Past research has widely explored the design and fabrication of resistive matrix-based tactile sensors for creating touch-sensitive devices. However, real-world deployment of resistive tactile sensing systems remains difficult for individuals with limited prior experience in embedded sensing due to challenges of portability, adaptivity, and efficiency. We introduce the WiReSens Toolkit, an accessible, open-source platform to bridge this gap. Central to our approach is adaptive hardware for interfacing with resistive sensors and a web-based GUI that streamlines access to advanced features for building scalable tactile sensing systems, including multi-device programming and wireless visualization across three communication protocols, autocalibration for adaptive sensitivity, and intermittent data transmission for low-power use. We validated the toolkit’s usability through a user study with 11 novice participants, who, on average, configured a tactile sensor with over 95% accuracy in under five minutes, calibrated sensors 10× faster than baseline methods, and showed improved sense-making of tactile data.

Simulating large-scale articulated assemblies poses a significant challenge due to the numerical stiffness and geometric complexity of jointed structures. Conventional rigid body solvers struggle with the high nonlinearity induced by rotation parameterization. This difficulty becomes more pronounced for multiple two-way-coupled bodies. This paper introduces a novel framework that leverages the linear kinematic mapping of Affine Body Dynamics (ABD). As ABD targets near-rigid objects, the constitutive variations of different materials become negligible, which justifies a co-rotational approach to isolate geometric nonlinearities of the system. This insight enables the use of constant system matrices that can be pre-factorized throughout the simulation, even with fully implicit integration schemes. To manage the high DOF counts of large-scale systems, we map primal body coordinates onto a compact dual space defined by minimal joint degrees of freedom. By solving the resulting KKT systems, our method ensures exact constraint enforcement and physically accurate motion propagation. We provide a suite of specialized solvers tailored for diverse joint topologies, including chains, trees, closed loops, and irregular networks. Experimental results show that our approach achieves interactive rates for systems with hundreds of thousands of bodies on a single CPU core, while maintaining excellent stability at large time steps.

We introduce Soft Anisotropic Diagrams (SAD), an explicit and differentiable image representation parameterized by a set of adaptive sites in the image plane. In SAD, each site specifies an anisotropic metric and an additively weighted distance score, and we compute pixel colors as a softmax blend over a small per-pixel top- K subset of sites. We induce a soft anisotropic additively weighted Voronoi partition (i.e., an Apollonius diagram) with learnable persite temperatures, preserving informative gradients while allowing clear, content-aligned boundaries and explicit ownership. Such a formulation enables efficient rendering by maintaining a per-query top- K map that approximates nearest neighbors under the same shading score, allowing GPU-friendly, fixed-size local computation. We update this list using our top- K propagation scheme inspired by jump flooding, augmented with stochastic injection to provide probabilistic global coverage. Training follows a GPU-first pipeline with gradient-weighted initialization, Adam optimization, and adaptive budget control through densification and pruning. Across standard benchmarks, SAD consistently outperforms Image-GS and Instant-NGP at matched bitrate. On Kodak, SAD reaches 46.0 dB PSNR with 2.2 s encoding time (vs. 28s for Image-GS), and delivers 4–19× end-to-end training speedups over state-of-the-art baselines. We demonstrate the effectiveness of SAD by showcasing the seamless integration with differentiable pipelines for forward and inverse problems, efficiency of fast random access, and compact storage. You can find the code here: https://luckyiyi.github.io/SAD.

CHI ’25, Yokohama, Japan

We introduce TetSphere Splatting, a Lagrangian geometry representation designed for high-quality 3D shape modeling. TetSphere splatting leverages an underused yet powerful geometric primitive -- volumetric tetrahedral meshes. It represents 3D shapes by deforming a collection of tetrahedral spheres, with geometric regularizations and constraints that effectively resolve common mesh issues such as irregular triangles, non-manifoldness, and floating artifacts. Experimental results on multi-view and single-view reconstruction highlight TetSphere splatting's superior mesh quality while maintaining competitive reconstruction accuracy compared to state-of-the-art methods. Additionally, TetSphere splatting demonstrates versatility by seamlessly integrating into generative modeling tasks, such as image-to-3D and text-to-3D generation.

Procedural materials, represented as functional node graphs, are ubiquitous in computer graphics for photorealistic material appearance design. They allow users to perform intuitive and precise editing to achieve desired visual appearances. However, creating a procedural material given an input image requires professional knowledge and significant effort. In this work, we leverage the ability to convert procedural materials into standard Python programs and fine-tune a large pre-trained vision-language model (VLM) to generate such programs from input images. To enable effective fine-tuning, we also contribute an open-source procedural material dataset and propose to perform program-level augmentation by prompting another pre-trained large language model (LLM). Through extensive evaluation, we show that our method outperforms previous methods on both synthetic and real-world examples.

While large language models (LLMs) have integrated images, adapting them to graphs remains challenging, limiting their applications in materials and drug design. This difficulty stems from the need for coherent autoregressive generation across texts and graphs. To address this, we introduce Llamole, the first multimodal LLM capable of interleaved text and graph generation, enabling molecular inverse design with retrosynthetic planning. Llamole integrates a base LLM with the Graph Diffusion Transformer and Graph Neural Networks for multi-conditional molecular generation and reaction inference within texts, while the LLM, with enhanced molecular understanding, flexibly controls activation among the different graph modules. Additionally, Llamole integrates A* search with LLM-based cost functions for efficient retrosynthetic planning. We create benchmarking datasets and conduct extensive experiments to evaluate Llamole against in-context learning and supervised fine-tuning. Llamole significantly outperforms 14 adapted LLMs across 12 metrics for controllable molecular design and retrosynthetic planning. Code and model at https://github.com/liugangcode/Llamole.

Designing synthetically accessible molecules and recommending analogs to unsynthesizable molecules are important problems for accelerating molecular discovery. We reconceptualize both problems using ideas from program synthesis. Drawing inspiration from syntax-guided synthesis approaches, we decouple the syntactic skeleton from the semantics of a synthetic tree to create a bilevel framework for reasoning about the combinatorial space of synthesis pathways. Given a molecule we aim to generate analogs for, we iteratively refine its skeletal characteristics via Markov Chain Monte Carlo simulations over the space of syntactic skeletons. Given a black-box oracle to optimize, we formulate a joint design space over syntactic templates and molecular descriptors and introduce evolutionary algorithms that optimize both syntactic and semantic dimensions synergistically. Our key insight is that once the syntactic skeleton is set, we can amortize over the search complexity of deriving the program's semantics by training policies to fully utilize the fixed horizon Markov Decision Process imposed by the syntactic template. We demonstrate performance advantages of our bilevel framework for synthesizable analog generation and synthesizable molecule design. Notably, our approach offers the user explicit control over the resources required to perform synthesis and biases the design space towards simpler solutions, making it particularly promising for autonomous synthesis platforms. Supporting code is at https://github.com/shiningsunnyday/SynthesisNet.

Directed acyclic graphs (DAGs) are a class of graphs commonly used in practice, with examples that include electronic circuits, Bayesian networks, and neural architectures. While many effective encoders exist for DAGs, it remains challenging to decode them in a principled manner, because the nodes of a DAG can have many different topological orders. In this work, we propose a grammar-based approach to constructing a principled, compact and equivalent sequential representation of a DAG. Specifically, we view a graph as derivations over an unambiguous grammar, where the DAG corresponds to a unique sequence of production rules. Equivalently, the procedure to construct such a description can be viewed as a lossless compression of the data. Such a representation has many uses, including building a generative model for graph generation, learning a latent space for property prediction, and leveraging the sequence representational continuity for Bayesian Optimization over structured data.

Recent data-efficient molecular generation approaches exploit graph grammars to introduce interpretability into the generative models. However, grammar learning therein relies on expert annotation or unreliable heuristics for algorithmic inference. We propose Foundation Molecular Grammar (FMG), which leverages multi-modal foundation models (MMFMs) to induce an interpretable molecular language. By exploiting the chemical knowledge of an MMFM, FMG renders molecules as images, describes them as text, and aligns information across modalities using prompt learning. FMG can be used as a drop-in replacement for the prior grammar learning approaches in molecular generation and property prediction. We show that FMG not only excels in synthesizability, diversity, and data efficiency but also offers built-in chemical interpretability for automated molecular discovery workflows. Code is available at https://github.com/shiningsunnyday/induction.

Differentiable simulation has become a powerful tool for system identification. While prior work has focused on identifying robot properties using robot-specific data or object properties using object-specific data, our approach calibrates object properties by using information from the robot, without relying on data from the object itself. Specifically, we utilize robot joint encoder information, which is commonly available in standard robotic systems. Our key observation is that by analyzing the robot's reactions to manipulated objects, we can infer properties of those objects, such as inertia and softness. Leveraging this insight, we develop differentiable simulations of robot-object interactions to inversely identify the properties of the manipulated objects. Our approach relies solely on proprioception – the robot's internal sensing capabilities – and does not require external measurement tools or vision-based tracking systems. This general method is applicable to any articulated robot and requires only joint position information. We demonstrate the effectiveness of our method on a low-cost robotic platform, achieving accurate mass and elastic modulus estimations of manipulated objects with just a few seconds of computation on a laptop.

The development of novel autonomous underwater gliders has been hindered by limited shape diversity, primarily due to the reliance on traditional design tools that depend heavily on manual trial and error. Building an automated design framework is challenging due to the complexities of representing glider shapes and the high computational costs associated with modeling complex solid-fluid interactions. In this work, we introduce an AI-enhanced automated computational framework designed to overcome these limitations by enabling the creation of underwater robots with non-trivial hull shapes. Our approach involves an algorithm that cooptimizes both shape and control signals, utilizing a reducedorder geometry representation and a differentiable neural-network-based fluid surrogate model. This end-to-end design workflow facilitates rapid iteration and evaluation of hydrodynamic performance, leading to the discovery of optimal and complex hull shapes across various control settings. We validate our method through wind tunnel experiments and swimming pool gliding tests, demonstrating that our computationally designed gliders surpass manually designed counterparts in terms of energy efficiency. By addressing challenges in efficient shape representation and neural fluid surrogate models, our work paves the way for the development of highly efficient underwater gliders, with implications for long-range ocean exploration and environmental monitoring.

In this paper, we present an adaptive walker system designed to address limitations in current intelligent walker technologies. While recent advancements have been made in this field, existing systems often struggle to seamlessly interpret user intent for speed control and lack adaptability across diverse scenarios and terrain. Our proposed solution incorporates high-resolution tactile sensors, deep learning algorithms, IMU sensors, and linear motors to dynamically adjust to the user's intentions and terrain changes. The system is capable of predicting the user's desired speed with an error margin of only 20.99%, relying solely on tactile input from hand and arm contact points. Additionally, it maintains the walker's horizontal stability with an error of less than 1 degree by adjusting leg lengths in response to variations in ground angle. This adaptive walker enhances user safety and comfort, particularly for individuals with reduced strength or cognitive abilities, and offers reliable assistance on uneven terrain such as uphill and downhill paths.

Accurate prediction of continuous properties is essential to many scientific and engineering tasks. Although deep-learning regressors excel with abundant labels, their accuracy deteriorates in data-scarce regimes. We introduce RankRefine, a model-agnostic, plug-and-play post-hoc refinement technique that injects expert knowledge through pairwise rankings. Given a query item and a small reference set with known properties, RankRefine combines the base regressor’s output with a rank-based estimate via inverse-variance weighting, requiring no retraining. In molecular property prediction task, RankRefine achieves up to 10\% relative reduction in mean absolute error using only 20 pairwise comparisons obtained through a general-purpose large language model (LLM) with no finetuning. As rankings provided by human experts or general-purpose LLMs are sufficient for improving regression across diverse domains, RankRefine offers practicality and broad applicability, especially in low-data settings.

Attention with bias, which extends standard attention by introducing prior knowledge as an additive bias matrix to the query-key scores, has been widely deployed in vision, language, protein-folding and other advanced scientific models, underscoring its status as a key evolution of this foundational module. However, introducing bias terms creates a severe efficiency bottleneck in attention computation. It disrupts the tightly fused memory-compute pipeline that underlies the speed of accelerators like FlashAttention, thereby stripping away most of their performance gains and leaving biased attention computationally expensive. Surprisingly, despite its common usage, targeted efficiency optimization for attention with bias remains absent, which seriously hinders its application in complex tasks. Diving into the computation of FlashAttention, we prove that its optimal efficiency is determined by the rank of the attention weight matrix. Inspired by this theoretical result, this paper presents FlashBias based on the low-rank compressed sensing theory, which can provide fast-exact computation for many widely used attention biases and a fast-accurate approximation for biases in general formalizations. FlashBias can fully take advantage of the extremely optimized matrix multiplication operation in modern GPUs, achieving 1.5$\times$ speedup for Pairformer in AlphaFold 3, and over 2$\times$ speedup for attention with bias in vision and language models without loss of accuracy. Code is available at this repository: https://github.com/thuml/FlashBias.

Rendering novel, relit views of a human head, given a monocular portrait image as input, is an inherently underconstrained problem. The traditional graphics solution is to explicitly decompose the input image into geometry, material and lighting via differentiable rendering; but this is constrained by the multiple assumptions and approximations of the underlying models and parameterizations of these scene components. We propose 3DPR, an image-based relighting model that leverages generative priors learnt from multi-view One-Light-at-A-Time (OLAT) images captured in a light stage. We introduce a new diverse and large-scale multi-view 4K OLAT dataset of 139 subjects to learn a high-quality prior over the distribution of high-frequency face reflectance. We leverage the latent space of a pre-trained generative head model that provides a rich prior over face geometry learnt from in-the-wild image datasets. The input portrait is first embedded in the latent manifold of such a model through an encoder-based inversion process. Then a novel triplane-based reflectance network trained on our lightstage data is used to synthesize high-fidelity OLAT images to enable image-based relighting. Our reflectance network operates in the latent space of the generative head model, crucially enabling a relatively small number of lightstage images to train the reflectance model. Combining the generated OLATs according to a given HDRI environment maps yields physically accurate environmental relighting results. Through quantitative and qualitative evaluations, we demonstrate that 3DPR outperforms previous methods, particularly in preserving identity and in capturing lighting effects such as specularities, self-shadows, and subsurface scattering.

Abstract Parametric CAD systems use domain‐specific languages (DSLs) to represent geometry as programs, enabling both flexible modeling and structured editing. With the rise of large language models (LLMs), there is growing interest in generating such programs from natural language. This raises a key question: what kind of DSL best supports both CAD generation and editing, whether performed by a human or an AI? In this work, we introduce AIDL, a hierarchical, solver‐aided DSL designed to align with the strengths of LLMs while remaining interpretable and editable by humans. AIDL enables high‐level reasoning by breaking problems into abstract components and structural relationships, while offloading low‐level geometric reasoning to a constraint solver. We evaluate AIDL in a 2D text‐to‐CAD setting using a zero‐shot prompt‐based interface and compare it to OpenSCAD, a widely used CAD DSL that appears in LLM training data. AIDL produces results that are visually competitive and significantly easier to edit. Our findings suggest that language design is a powerful complement to model training and prompt engineering for building collaborative AI–human tools in CAD. Code is available at https://github.com/deGravity/aidl .

The realism of digital avatars is crucial in enabling telepresence applications with self-expression and customization. While physical simulations can produce realistic motions for clothed humans, they require high-quality garment assets with associated physical parameters for cloth simulations. However, manually creating these assets and calibrating their parameters is labor-intensive and requires specialized expertise. Current methods focus on reconstructing geometry, but don't generate complete assets for physics-based applications. To address this gap, we propose DiffAvatar, a novel approach that performs body and garment co-optimization using differentiable simulation. By integrating physical simulation into the optimization loop and accounting for the complex nonlinear behavior of cloth and its intricate interaction with the body, our framework recovers body and garment geometry and extracts important material parameters in a physically plausible way. Our experiments demonstrate that our approach generates realistic clothing and body shape suitable for downstream applications. We provide additional insights and results on our webpage: people. csail. mit. edu/liyifei/publication/diffavatar.

Shape assembly composes complex shapes geometries by arranging simple part geometries and has wide applications in autonomous robotic assembly and CAD modeling. Existing works focus on geometry reasoning and neglect the actual physical assembly process of matching and fitting joints, which are the contact surfaces connecting different parts. In this paper, we consider contacting joints for the task of multi-part assembly. A successful joint-optimized assembly needs to satisfy the bilateral objectives of shape structure and joint alignment. We propose a hierarchical graph learning approach composed of two levels of graph representation learning. The part graph takes part geometries as input to build the desired shape structure. The joint-level graph uses part joints information and focuses on matching and aligning joints. The two kinds of information are combined to achieve the bilateral objectives. Extensive experiments demonstrate that our method outperforms previous methods, achieving better shape structure and higher joint alignment accuracy.

Modeling and analyzing object and shape has been well studied in the past. However, manipulation of these complex tools and articulated objects remains difficult for autonomous agents. Our human hands, however, are dexterous and adaptive. We can easily adapt a manipulation skill on one object to all objects in the class and to other similar classes. Our intuition comes from that there is a close connection between manipulations and topology and articulation of objects. The possible articulation of objects indicates the types of manipulation necessary to operate the object. In this work, we aim to take a manipulation perspective to understand everyday objects and tools. We collect a multi-modal visual-tactile dataset that contains paired full-hand force pressure maps and manipulation videos. We also propose a novel method to learn a cross-modal latent manifold that allow for cross-modal prediction and discovery of latent structure in different data modalities. We conduct extensive experiments to demonstrate the effectiveness of our method.

Large Language Models have recently gained significant attention in scientific discovery for their extensive knowledge and advanced reasoning capabilities. However, they encounter challenges in effectively simulating observational feedback and grounding it with language to propel advancements in physical scientific discovery. Conversely, human scientists undertake scientific discovery by formulating hypotheses, conducting experiments, and revising theories through observational analysis. Inspired by this, we propose to enhance the knowledge-driven, abstract reasoning abilities of LLMs with the computational strength of simulations. We introduce Scientific Generative Agent (SGA), a bilevel optimization framework: LLMs act as knowledgeable and versatile thinkers, proposing scientific hypotheses and reason about discrete components, such as physics equations or molecule structures; meanwhile, simulations function as experimental platforms, providing observational feedback and optimizing via differentiability for continuous parts, such as physical parameters. We conduct extensive experiments to demonstrate our framework’s efficacy in constitutive law discovery and molecular design, unveiling novel solutions that differ from conventional human expectations yet remain coherent upon analysis.

Recent research in molecular discovery has primarily been devoted to small, drug-like molecules, leaving many similarly important applications in material design without adequate technology. These applications often rely on more complex molecular structures with fewer examples that are carefully designed using known substructures. We propose a data-efficient and interpretable model for representing and reasoning over such molecules in terms of graph grammars that explicitly describe the hierarchical design space featuring motifs to be the design basis. We present a novel representation in the form of random walks over the design space, which facilitates both molecule generation and property prediction. We demonstrate clear advantages over existing methods in terms of performance, efficiency, and synthesizability of predicted molecules, and we provide detailed insights into the method’s chemical interpretability.

Bayesian optimization has been successfully applied to optimize black-box functions where the number of evaluations is severely limited. However, in many real-world applications, it is hard or impossible to know in advance which designs are feasible due to some physical or system limitations. These issues lead to an even more challenging problem of optimizing an unknown function with unknown constraints. In this paper, we observe that in such scenarios optimal solution typically lies on the boundary between feasible and infeasible regions of the design space, making it considerably more difficult than that with interior optima. Inspired by this observation, we propose BE-CBO, a new Bayesian optimization method that efficiently explores the boundary between feasible and infeasible designs. To identify the boundary, we learn the constraints with an ensemble of neural networks that outperform the standard Gaussian Processes for capturing complex boundaries. Our method demonstrates superior performance against state-of-the-art methods through comprehensive experiments on synthetic and real-world benchmarks. Code available at: https://github.com/yunshengtian/BE-CBO

Despite recent exponential advancements in computer vision and reinforcement learning, it remains challenging for robots to interact with liquids. These challenges are particularly pronounced due to the limitations imposed by opaque containers, transparent liquids, fine-grained splashes, and visual obstructions arising from the robot’s own manipulation activities. Yet, there exists a substantial opportunity for robotics to excel in liquid identification and manipulation, given its potential role in chemical handling in laboratories and various manufacturing sectors such as pharmaceuticals or beverages. In this work, we present a novel approach for liquid class identification and state estimation leveraging electrical impedance sensing. We design and mount a digitally embroidered electrode array to a commercial robot gripper. Coupled with a customized impedance sensing board, we collect data on liquid manipulation with a swept frequency sensing mode and a frequency-specific impedance measuring mode. Our developed learning-based model achieves an accuracy of 93.33% in classifying 9 different types of liquids (8 liquids + air), and 97.65% in estimating the liquid state. We investigate the effectiveness of our system with a series of ablation studies. These findings highlight our work as a promising solution for enhancing robotic manipulation in liquid-related tasks.

The automated assembly of complex products requires a system that can automatically plan a physically feasible sequence of actions for assembling many parts together. In this paper, we present ASAP, a physics-based planning approach for automatically generating such a sequence for general-shaped assemblies. ASAP accounts for gravity to design a sequence where each sub-assembly is physically stable with a limited number of parts being held and a support surface. We apply efficient tree search algorithms to reduce the combinatorial complexity of determining such an assembly sequence. The search can be guided by either geometric heuristics or graph neural networks trained on data with simulation labels. Finally, we show the superior performance of ASAP at generating physically realistic assembly sequence plans on a large dataset of hundreds of complex product assemblies. We further demonstrate the applicability of ASAP on both simulation and real-world robotic setups. Project website: asap.csail.mit.edu

We present NeuralFluid, a novel framework to explore neural control and design of complex fluidic systems with dynamic solid boundaries. Our system features a fast differentiable Navier-Stokes solver with solid-fluid interface handling, a low-dimensional differentiable parametric geometry representation, a control-shape co-design algorithm, and gym-like simulation environments to facilitate various fluidic control design applications. Additionally, we present a benchmark of design, control, and learning tasks on high-fidelity, high-resolution dynamic fluid environments that pose challenges for existing differentiable fluid simulators. These tasks include designing the control of artificial hearts, identifying robotic end-effector shapes, and controlling a fluid gate. By seamlessly incorporating our differentiable fluid simulator into a learning framework, we demonstrate successful design, control, and learning results that surpass gradient-free solutions in these benchmark tasks.

We present a computational framework that transforms single images into 3D physical objects. The visual geometry of a physical object in an image is determined by three orthogonal attributes: mechanical properties, external forces, and rest-shape geometry. Existing single-view 3D reconstruction methods often overlook this underlying composition, presuming rigidity or neglecting external forces. Consequently, the reconstructed objects fail to withstand real-world physical forces, resulting in instability or undesirable deformation -- diverging from their intended designs as depicted in the image. Our optimization framework addresses this by embedding physical compatibility into the reconstruction process. We explicitly decompose the three physical attributes and link them through static equilibrium, which serves as a hard constraint, ensuring that the optimized physical shapes exhibit desired physical behaviors. Evaluations on a dataset collected from Objaverse demonstrate that our framework consistently enhances the physical realism of 3D models over existing methods. The utility of our framework extends to practical applications in dynamic simulations and 3D printing, where adherence to physical compatibility is paramount.

Robots are often built from standardized assemblies, (e.g. arms, legs, or fingers), but each robot must be trained from scratch to control all the actuators of all the parts together. In this paper we demonstrate a new approach that takes a single robot and its controller as input and produces a set of modular controllers for each of these assemblies such that when a new robot is built from the same parts, its control can be quickly learned by reusing the modular controllers. We achieve this with a framework called MeMo which learns (Me)aningful, (Mo)dular controllers. Specifically, we propose a novel modularity objective to learn an appropriate division of labor among the modules. We demonstrate that this objective can be optimized simultaneously with standard behavior cloning loss via noise injection. We benchmark our framework in locomotion and grasping environments on simple to complex robot morphology transfer. We also show that the modules help in task transfer. On both structure and task transfer, MeMo achieves improved training efficiency to graph neural network and Transformer baselines.

Abstract Portrait viewpoint and illumination editing is an important problem with several applications in VR/AR, movies, and photography. Comprehensive knowledge of geometry and illumination is critical for obtaining photorealistic results. Current methods are unable to explicitly model in 3D while handling both viewpoint and illumination editing from a single image. In this paper, we propose VoRF, a novel approach that can take even a single portrait image as input and relight human heads under novel illuminations that can be viewed from arbitrary viewpoints. VoRF represents a human head as a continuous volumetric field and learns a prior model of human heads using a coordinate-based MLP with individual latent spaces for identity and illumination. The prior model is learned in an auto-decoder manner over a diverse class of head shapes and appearances, allowing VoRF to generalize to novel test identities from a single input image. Additionally, VoRF has a reflectance MLP that uses the intermediate features of the prior model for rendering One-Light-at-A-Time (OLAT) images under novel views. We synthesize novel illuminations by combining these OLAT images with target environment maps. Qualitative and quantitative evaluations demonstrate the effectiveness of VoRF for relighting and novel view synthesis, even when applied to unseen subjects under uncontrolled illumination. This work is an extension of Rao et al. (VoRF: Volumetric Relightable Faces 2022). We provide extensive evaluation and ablative studies of our model and also provide an application, where any face can be relighted using textual input.

We propose the Medial Skeletal Diagram, a novel skeletal representation that tackles the prevailing issues around skeleton sparsity and reconstruction accuracy in existing skeletal representations. Our approach augments the continuous elements in the medial axis representation to effectively shift the complexity away from the discrete elements. To that end, we introduce generalized enveloping primitives, an enhancement over the standard primitives in the medial axis, which ensure efficient coverage of intricate local features of the input shape and substantially reduce the number of discrete elements required. Moreover, we present a computational framework for constructing a medial skeletal diagram from an arbitrary closed manifold mesh. Our optimization pipeline ensures that the resulting medial skeletal diagram comprehensively covers the input shape with the fewest primitives. Additionally, each optimized primitive undergoes a post-refinement process to guarantee an accurate match with the source mesh in both geometry and tessellation. We validate our approach on a comprehensive benchmark of 100 shapes, demonstrating the sparsity of the discrete elements and superior reconstruction accuracy across a variety of cases. Finally, we exemplify the versatility of our representation in downstream applications such as shape generation, mesh decomposition, shape optimization, mesh alignment, mesh compression, and user-interactive design.

Modern 3D content creation heavily relies on procedural assets. In particular, procedural materials are ubiquitous in the industry, but their manipulation remains challenging. Previous work [Hu et al. 2023] conditionally generates procedural graphs that match a given input image. However, the parameter generation step limits how accurately the generated graph matches the input image, due to a reliance on supervision with scarcely available procedural data. We propose to improve parameter prediction accuracy for image-conditioned procedural material generation by leveraging reinforcement learning (RL) and present the first RL approach for procedural materials. RL circumvents the limited availability of procedural data, the domain gap between real and synthetic materials, and the need for end-to-end differentiable loss functions. Given a target image, we retrieve a procedural material and use an RL-trained transformer model to predict a set of parameters that reconstruct the target image as closely as possible. We show that using RL significantly improves parameter prediction to match a given target image compared to supervised methods on both synthetic and real target images.

We propose a hybrid neural network (NN) and PDE approach for learning generalizable PDE dynamics from motion observations. Many NN approaches learn an end-to-end model that implicitly models both the governing PDE and constitutive models (or material models). Without explicit PDE knowledge, these approaches cannot guarantee physical correctness and have limited generalizability. We argue that the governing PDEs are often well-known and should be explicitly enforced rather than learned. Instead, constitutive models are particularly suitable for learning due to their data-fitting nature. To this end, we introduce a new framework termed "Neural Constitutive Laws" (NCLaw), which utilizes a network architecture that strictly guarantees standard constitutive priors, including rotation equivariance and undeformed state equilibrium. We embed this network inside a differentiable simulation and train the model by minimizing a loss function based on the difference between the simulation and the motion observation. We validate NCLaw on various large-deformation dynamical systems, ranging from solids to fluids. After training on a single motion trajectory, our method generalizes to new geometries, initial/boundary conditions, temporal ranges, and even multi-physics systems. On these extremely out-of-distribution generalization tasks, NCLaw is orders-of-magnitude more accurate than previous NN approaches. Real-world experiments demonstrate our method’s ability to learn constitutive laws from videos.

The prediction of molecular properties is a crucial task in the field of material and drug discovery. The potential benefits of using deep learning techniques are reflected in the wealth of recent literature. Still, these techniques are faced with a common challenge in practice: Labeled data are limited by the cost of manual extraction from literature and laborious experimentation. In this work, we propose a data-efficient property predictor by utilizing a learnable hierarchical molecular grammar that can generate molecules from grammar production rules. Such a grammar induces an explicit geometry of the space of molecular graphs, which provides an informative prior on molecular structural similarity. The property prediction is performed using graph neural diffusion over the grammar-induced geometry. On both small and large datasets, our evaluation shows that this approach outperforms a wide spectrum of baselines, including supervised and pre-trained graph neural networks. We include a detailed ablation study and further analysis of our solution, showing its effectiveness in cases with extremely limited data.

Efficient numerical solvers for partial differential equations empower science and engineering. One commonly employed numerical solver is the preconditioned conjugate gradient (PCG) algorithm, whose performance is largely affected by the preconditioner quality. However, designing high-performing preconditioner with traditional numerical methods is highly non-trivial, often requiring problem-specific knowledge and meticulous matrix operations. We present a new method that leverages learning-based approach to obtain an approximate matrix factorization to the system matrix to be used as a preconditioner in the context of PCG solvers. Our high-level intuition comes from the shared property between preconditioners and network-based PDE solvers that excels at obtaining approximate solutions at a low computational cost. Such observation motivates us to represent preconditioners as graph neural networks (GNNs). In addition, we propose a new loss function that rewrites traditional preconditioner metrics to incorporate inductive bias from PDE data distributions, enabling effective training of high-performing preconditioners. We conduct extensive experiments to demonstrate the efficacy and generalizability of our proposed approach on solving various 2D and 3D linear second-order PDEs.

Holographic displays generate Three-Dimensional (3D) images by displaying single-color holograms time-sequentially, each lit by a single-color light source. However, representing each color one by one limits brightness in holographic displays. This paper introduces a new driving scheme for realizing brighter images in holographic displays. Unlike the conventional driving scheme, our method utilizes three light sources to illuminate each displayed hologram simultaneously at various intensity levels. In this way, our method reconstructs a multiplanar three-dimensional target scene using consecutive multi-color holograms and persistence of vision. We co-optimize multi-color holograms and required intensity levels from each light source using a gradient descent-based optimizer with a combination of application-specific loss terms. We experimentally demonstrate that our method can increase the intensity levels in holographic displays up to three times, reaching a broader range and unlocking new potentials for perceptual realism in holographic displays.

We propose a hybrid neural network and physics framework for reduced-order modeling of elastoplasticity and fracture. State-of-the-art scientific computing models like the Material Point Method (MPM) faithfully simulate large-deformation elastoplasticity and fracture mechanics. However, their long runtime and large memory consumption render them unsuitable for applications constrained by computation time and memory usage, e.g., virtual reality. To overcome these barriers, we propose a reduced-order framework. Our key innovation is training a low-dimensional manifold for the Kirchhoff stress field via an implicit neural representation. This low-dimensional neural stress field (NSF) enables efficient evaluations of stress values and, correspondingly, internal forces at arbitrary spatial locations. In addition, we also train neural deformation and affine fields to build low-dimensional manifolds for the deformation and affine momentum fields. These neural stress, deformation, and affine fields share the same low-dimensional latent space, which uniquely embeds the high-dimensional simulation state. After training, we run new simulations by evolving in this single latent space, which drastically reduces the computation time and memory consumption. Our general continuum-mechanics-based reduced-order framework is applicable to any phenomena governed by the elastodynamics equation. To showcase the versatility of our framework, we simulate a wide range of material behaviors, including elastica, sand, metal, non-Newtonian fluids, fracture, contact, and collision. We demonstrate dimension reduction by up to 100,000 × and time savings by up to 10 ×.

Wearable devices like smartwatches and smart wristbands have gained substantial popularity in recent years. However, their small interfaces create inconvenience and limit computing functionality. To fill this gap, we propose ViWatch, which enables robust finger interactions under deployment variations, and relies on a single IMU sensor that is ubiquitous in COTS smartwatches. To this end, we design an unsupervised Siamese adversarial learning method. We built a real-time system on commodity smartwatches and tested it with over one hundred volunteers. Results show that the system accuracy is about 97% over a week. In addition, it is resistant to deployment variations such as different hand shapes, finger activity strengths, and smartwatch positions on the wrist. We also developed a number of mobile applications using our interactive system and conducted a user study where all participants preferred our un-supervised approach to supervised calibration. The demonstration of ViWatch is shown at https://youtu.be/N5-ggvy2qfI.

In this paper, we introduce MagKnitic, a novel approach to integrate passive force feedback and binary sensing into fabrics via digital machine knitting. Our approach utilizes digital fabrication technology to enable haptic interfaces that are soft, flexible, lightweight, and conform to the user’s body shape. Despite these characteristics, our interfaces provide diverse, interactive, and responsive force feedback, expanding the design space for haptic experiences.MagKnitic provides scalable and customizable passive haptic sensations by utilizing the attractive force between ferromagnetic yarns and permanent magnets, both of which are seamlessly integrated into knitted fabrics. Moreover, we present a binary sensing capability based on the resistance drop resulting from the activated electrical path between the integrated magnets and ferromagnetic yarn upon direct contact. We offer parametric design templates for users to customize MagKnitic layouts and patterns. With various design layouts and combinations, MagKnitic supports passive haptics interactions of linear, polar, angular, planar, radial, and user-defined motions. We perform a technical evaluation of the passive force feedback and the binary sensing capabilities with different machine knitting layouts and patterns, embedded magnet sizes, and interaction distances. In addition, we conduct two user studies to validate the effectiveness of MagKnitic. Finally, we demonstrate various application scenarios, including wearable input interfaces, game controllers, passive VR/AR wearables, and interactive furniture coverings.

Packing 3D objects into a known container is a very common task in many industries such as packaging, transportation, and manufacturing. This important problem is known to be NP-hard and even approximate solutions are challenging. This is due to the difficulty of handling interactions between objects with arbitrary 3D geometries and a vast combinatorial search space. Moreover, the packing must be interlocking-free for real-world applications. In this work, we first introduce a novel packing algorithm to search for placement locations given an object. Our method leverages a discrete voxel representation. We formulate collisions between objects as correlations of functions computed efficiently using Fast Fourier Transform (FFT). To determine the best placements, we utilize a novel cost function, which is also computed efficiently using FFT. Finally, we show how interlocking detection and correction can be addressed in the same framework resulting in interlocking-free packing. We propose a challenging benchmark with thousands of 3D objects to evaluate our algorithm. Our method demonstrates state-of-the-art performance on the benchmark when compared to existing methods in both density and speed.

Cloth simulation has wide applications in computer animation, garment design, and robot-assisted dressing. This work presents a differentiable cloth simulator whose additional gradient information facilitates cloth-related applications. Our differentiable simulator extends a state-of-the-art cloth simulator based on Projective Dynamics (PD) and with dry frictional contact [Ly et al. 2020 ]. We draw inspiration from previous work [Du et al. 2021 ] to propose a fast and novel method for deriving gradients in PD-based cloth simulation with dry frictional contact. Furthermore, we conduct a comprehensive analysis and evaluation of the usefulness of gradients in contact-rich cloth simulation. Finally, we demonstrate the efficacy of our simulator in a number of downstream applications, including system identification, trajectory optimization for assisted dressing, closed-loop control, inverse design, and real-to-sim transfer. We observe a substantial speedup obtained from using our gradient information in solving most of these applications.

Node-graph-based procedural materials are vital to 3D content creation within the computer graphics industry. Leveraging the expressive representation of procedural materials, artists can effortlessly generate diverse appearances by altering the graph structure or node parameters. However, manually reproducing a specific appearance is a challenging task that demands extensive domain knowledge and labor. Previous research has sought to automate this process by converting artist-created material graphs into differentiable programs and optimizing node parameters against a photographed material appearance using gradient descent. These methods involve implementing differentiable filter nodes [Shi et al. 2020] and training differentiable neural proxies for generator nodes to optimize continuous and discrete node parameters [Hu et al. 2022a] jointly. Nevertheless, Neural Proxies exhibits critical limitations, such as long training times, inaccuracies, fixed resolutions, and confined parameter ranges, which hinder their scalability towards the broad spectrum of production-grade material graphs. These constraints fundamentally stem from the absence of faithful and efficient implementations of generic noise and pattern generator nodes, both differentiable and non-differentiable. Such deficiency prevents the direct optimization of continuous and discrete generator node parameters without relying on surrogate models. We present Diffmat v2 , an improved differentiable procedural material library, along with a fully-automated, end-to-end procedural material capture framework that combines gradient-based optimization and gradient-free parameter search to match existing production-grade procedural materials against user-taken flash photos. Diffmat v2 expands the range of differentiable material graph nodes in Diffmat [Shi et al. 2020] by adding generic noise/pattern generator nodes and user-customizable per-pixel filter nodes. This allows for the complete translation and optimization of procedural materials across various categories without the need for external proprietary tools or pre-cached noise patterns. Consequently, our method can capture a considerably broader array of materials, encompassing those with highly regular or stochastic geometries. We demonstrate that our end-to-end approach yields a closer match to the target than MATch [Shi et al. 2020] and Neural Proxies [Hu et al. 2022a] when starting from initially unmatched continuous and discrete parameters.

We introduce a compact, intuitive procedural graph representation for cellular metamaterials, which are small-scale, tileable structures that can be architected to exhibit many useful material properties. Because the structures’ “architectures” vary widely—with elements such as beams, thin shells, and solid bulks—it is difficult to explore them using existing representations. Generic approaches like voxel grids are versatile, but it is cumbersome to represent and edit individual structures; architecture-specific approaches address these issues, but are incompatible with one another. By contrast, our procedural graph succinctly represents the construction process for any structure using a simple skeleton annotated with spatially varying thickness. To express the highly constrained triply periodic minimal surfaces (TPMS) in this manner, we present the first fully automated version of the conjugate surface construction method, which allows novices to create complex TPMS from intuitive input. We demonstrate our representation’s expressiveness, accuracy, and compactness by constructing a wide range of established structures and hundreds of novel structures with diverse architectures and material properties. We also conduct a user study to verify our representation’s ease-of-use and ability to expand engineers’ capacity for exploration.

Soft actuators with integrated sensing have shown utility in a variety of applications such as assistive wearables, robotics, and interactive input devices. Despite their promise, these actuators can be difficult to both design and fabricate. As a solution, we present a workflow for computationally designing and digitally fabricating soft pneumatic actuators via a machine knitting process. Machine knitting is attractive as a fabrication process because it is fast, digital (programmable), and provides access to a rich material library of functional yarns for specified mechanical behavior and integrated sensing. Our method uses elastic stitches to construct non-homogeneous knitting structures, which program the bending of actuators when inflated. Our method also integrates pressure and swept frequency capacitive sensing structures using conductive yarns. The entire knitted structure is fabricated automatically in a single machine run. We further provide a computational design interface for the user to interactively preview actuators’ quasi-static shape when authoring elastic stitches. Our sensing-integrated actuators are cost-effective, easy to design, robust to large actuation, and require minimal manual post-processing. We demonstrate five use-cases of our actuators in relevant application settings.

Physical products are often complex assemblies combining a multitude of 3D parts modeled in computer-aided design (CAD) software. CAD designers build up these assemblies by aligning individual parts to one another using constraints called joints. In this paper we introduce JoinABLe, a learning-based method that assembles parts together to form joints. JoinABLe uses the weak supervision available in standard parametric CAD files without the help of object class labels or human guidance. Our results show that by making network predictions over a graph representation of solid models we can outperform multiple baseline methods with an accuracy (79.53%) that approaches human performance (80%). Finally, to support future research we release the Fusion 360 Gallery assembly dataset, containing assemblies with rich information on joints, contact surfaces, holes, and the underlying assembly graph structure.

Aquatic locomotion is a classic fluid-structure interaction (FSI) problem of interest to biologists and engineers. Solving the fully coupled FSI equations for incompressible Navier-Stokes and finite elasticity is computationally expensive. Optimizing robotic swimmer design within such a system generally involves cumbersome, gradient-free procedures on top of the already costly simulation. To address this challenge we present a novel, fully differentiable hybrid approach to FSI that combines a 2D direct numerical simulation for the deformable solid structure of the swimmer and a physics-constrained neural network surrogate to capture hydrodynamic effects of the fluid. For the deformable solid simulation of the swimmer’s body, we use state-of-the-art techniques from the field of computer graphics to speed up the finite-element method (FEM). For the fluid simulation, we use a U-Net architecture trained with a physics-based loss function to predict the flow field at each time step. The pressure and velocity field outputs from the neural network are sampled around the boundary of our swimmer using an immersed boundary method (IBM) to compute its swimming motion accurately and efficiently. We demonstrate the computational efficiency and differentiability of our hybrid simulator on a 2D carangiform swimmer. Due to differentiability, the simulator can be used for computational design of controls for soft bodies immersed in fluids via direct gradient-based optimization.

Autonomous underwater vehicles (AUVs) are spe-cialized robots that are commonly used for seafloor surveying and ocean water sampling. Computational design approaches have emerged to reduce the effort required to design both individual AUVs as well as fleets. As the number and scale of underwater missions increases beyond the capabilities of a single vehicle, fleet level design will become more important. Depending on the mission, the optimal fleet may consist of multiple distinct types of AUVs designed to a variety of specifications. Moreover, the AUVs may differ in both continuous parameters (such as battery capacity) and discrete parameters (such as number and model of thrusters). In this work, we present a computational pipeline for designing these heterogeneous AUV fleets. Using a novel shape design space based on a graph grammar and deformation cages, we can express a variety of AUV architectures with different topologies, component selections, and dimensions. We search this space using a combination of discrete graph search and gradient-based continuous optimization, enabled by a differentiable AUV simulator. Finally, we formulate heterogeneous fleet design as a modified knapsack problem, and solve it using an efficient backtracking-based algorithm. We evaluate our pipeline on a simulated mission with nonuniform design requirements-surveying a section of seafloor with varying depth-and show that the best heterogeneous fleet outperforms the best fleet composed of a single vehicle type.

Traditional robotic manipulator design methods require extensive, time-consuming, and manual trial and error to produce a viable design. During this process, engineers often spend their time redesigning or reshaping components as they discover better topologies for the robotic manipula-tor. Tactile sensors, while useful, often complicate the design due to their bulky form factor. We propose an integrated design pipeline to streamline the design and manufacturing of robotic manipulators with knitted, glove-like tactile sensors. The proposed pipeline allows a designer to assemble a collection of modular, open-source components by applying predefined graph grammar rules. The end result is an intuitive design paradigm that allows the creation of new virtual designs of manipulators in a matter of minutes. Our framework allows the designer to fine-tune the manipulator's shape through cage-based geometry deformation. Finally, the designer can select surfaces for adding tactile sensing. Once the manipulator design is finished, the program will automatically generate 3D printing and knitting files for manufacturing. We demonstrate the utility of this pipeline by creating four custom manipulators tested on real-world tasks: screwing in a wing nut, pouring water from a bottle, picking up an egg, and cutting paper with scissors.

Accurate simulation of soft mechanisms under dynamic actuation is critical for the design of soft robots. We address this gap with our differentiable simulation tool by learning the material parameters of our soft robotic fish. On the example of a soft robotic fish, we demonstrate an experimentally-verified, fast optimization pipeline for learning the material parameters from quasi-static data via differentiable simulation and apply it to the prediction of dynamic performance. Our method identifies physically plausible Young's moduli for various soft silicone elastomers and stiff acetal copolymers used in creation of our three different robotic fish tail designs. We show that our method is compatible with varying internal geometry of the actuators, such as the number of hollow cavities. Our framework allows high fidelity prediction of dynamic behavior for composite bi-morph bending structures in real hardware to millimeter-accuracy and within 3% error normalized to actuator length. We provide a differentiable and robust estimate of the thrust force using a neural network thrust predictor; this estimate allows for accurate modeling of our experimental setup measuring bollard pull. This work presents a prototypical hardware and simulation problem solved using our differentiable framework; the framework can be applied to higher dimensional parameter inference, learning control policies, and computational design due to its differentiable character.

Unmanned aerial vehicles (UAVs) have broad applications including disaster response, transportation, photography, and mapping. A significant bottleneck in the development of UAVs is the limited availability of automatic tools for task-specific co-design of a UAV's shape and controller. The development of such tools is particularly challenging as UAVs can take many forms, including fixed-wing planes, radial copters, and hybrid topologies, with each class of topology showing different advantages. In this work, we present a computational design pipeline for UAVs based on a graph grammar that can search across a wide range of topologies. Graphs generated by the grammar encode different topologies and component selections, while continuous parameters encode the dimensions and properties of each component. We further augment the shape representation with deformation cages, which allow expressing a variety of wing shapes. Each UAV design is associated with an LQR controller with tunable continuous parameters. To search over this complex discrete and continuous design space, we develop a hybrid algorithm that combines discrete graph search strategies and gradient-based continuous optimization methods using a differentiable UAV simulator. We evaluate our pipeline on a set of simulated flight tasks requiring dynamic motions, showing that it discovers novel UAV designs that outperform canonical UAVs typically made by engineers.

This paper introduces ActionSense, a multimodal dataset and recording framework with an emphasis on wearable sensing in a kitchen environment. It provides rich, synchronized data streams along with ground truth data to facilitate learning pipelines that could extract insights about how humans interact with the physical world during activities of daily living, and help lead to more capable and collaborative robot assistants. The wearable sensing suite captures motion, force, and attention information; it includes eye tracking with a first-person camera, forearm muscle activity sensors, a body-tracking system using 17 inertial sensors, finger-tracking gloves, and custom tactile sensors on the hands that use a matrix of conductive threads. This is coupled with activity labels and with externally-captured data from multiple RGB cameras, a depth camera, and microphones. The specific tasks recorded in ActionSense are designed to highlight lower-level physical skills and higher-level scene reasoning or action planning. They include simple object manipulations (e.g., stacking plates), dexterous actions (e.g., peeling or cutting vegetables), and complex action sequences (e.g., setting a table or loading a dishwasher). The resulting dataset and underlying experiment framework are available at https://action-sense.csail.mit.edu. Preliminary networks and analyses explore modality subsets and cross-modal correlations. ActionSense aims to support applications including learning from demonstrations, dexterous robot control, cross-modal predictions, and fine-grained action segmentation. It could also help inform the next generation of smart textiles that may one day unobtrusively send rich data streams to in-home collaborative or autonomous robot assistants.

We present a novel, fast differentiable simulator for soft-body learning and control applications. Existing differentiable soft-body simulators can be classified into two categories based on their time integration methods: Simulators using explicit timestepping schemes require tiny timesteps to avoid numerical instabilities in gradient computation, and simulators using implicit time integration typically compute gradients by employing the adjoint method and solving the expensive linearized dynamics. Inspired by Projective Dynamics ( PD ), we present Differentiable Projective Dynamics ( DiffPD ), an efficient differentiable soft-body simulator based on PD with implicit time integration. The key idea in DiffPD is to speed up backpropagation by exploiting the prefactorized Cholesky decomposition in forward PD simulation. In terms of contact handling, DiffPD supports two types of contacts: a penalty-based model describing contact and friction forces and a complementarity-based model enforcing non-penetration conditions and static friction. We evaluate the performance of DiffPD and observe it is 4–19 times faster compared with the standard Newton’s method in various applications including system identification, inverse design problems, trajectory optimization, and closed-loop control. We also apply DiffPD in a reality-to-simulation ( real-to-sim ) example with contact and collisions and show its capability of reconstructing a digital twin of real-world scenes.

Fluidic devices are crucial components in many industrial applications involving fluid mechanics. Computational design of a high-performance fluidic system faces multifaceted challenges regarding its geometric representation and physical accuracy. We present a novel topology optimization method to design fluidic devices in a Stokes flow context. Our approach is featured by its capability in accommodating a broad spectrum of boundary conditions at the solid-fluid interface. Our key contribution is an anisotropic and differentiable constitutive model that unifies the representation of different phases and boundary conditions in a Stokes model, enabling a topology optimization method that can synthesize novel structures with accurate boundary conditions from a background grid discretization. We demonstrate the efficacy of our approach by conducting several fluidic system design tasks with over four million design parameters.

Enabling additive manufacturing to employ a wide range of novel, functional materials can be a major boost to this technology. However, making such materials printable requires painstaking trial-and-error by an expert operator, as they typically tend to exhibit peculiar rheological or hysteresis properties. Even in the case of successfully finding the process parameters, there is no guarantee of print-to-print consistency due to material differences between batches. These challenges make closed-loop feedback an attractive option where the process parameters are adjusted on-the-fly. There are several challenges for designing an efficient controller: the deposition parameters are complex and highly coupled, artifacts occur after long time horizons, simulating the deposition is computationally costly, and learning on hardware is intractable. In this work, we demonstrate the feasibility of learning a closed-loop control policy for additive manufacturing using reinforcement learning. We show that approximate, but efficient, numerical simulation is sufficient as long as it allows learning the behavioral patterns of deposition that translate to real-world experiences. In combination with reinforcement learning, our model can be used to discover control policies that outperform baseline controllers. Furthermore, the recovered policies have a minimal sim-to-real gap. We showcase this by applying our control policy in-vivo on a single-layer printer using low and high viscosity materials.

Assembly planning is the core of automating product assembly, maintenance, and recycling for modern industrial manufacturing. Despite its importance and long history of research, planning for mechanical assemblies when given the final assembled state remains a challenging problem. This is due to the complexity of dealing with arbitrary 3D shapes and the highly constrained motion required for real-world assemblies. In this work, we propose a novel method to efficiently plan physically plausible assembly motion and sequences for real-world assemblies. Our method leverages the assembly-by-disassembly principle and physics-based simulation to efficiently explore a reduced search space. To evaluate the generality of our method, we define a large-scale dataset consisting of thousands of physically valid industrial assemblies with a variety of assembly motions required. Our experiments on this new benchmark demonstrate we achieve a state-of-the-art success rate and the highest computational efficiency compared to other baseline algorithms. Our method also generalizes to rotational assemblies (e.g., screws and puzzles) and solves 80-part assemblies within several minutes.

With the recent interest in wearable electronics and smart garments, digital fabrication of sensing and interactive textiles is in increasing demand. Recently, advances in digital machine knitting offer opportunities for the programmable, rapid fabrication of soft, breathable textiles. In this paper, we present KnitUI, a novel, accessible machine-knitted user interface based on resistive pressure sensing. Employing conductive yarns and various machine knitting techniques, we computationally design and automatically fabricate the double-layered resistive sensing structures as well as the coupled conductive connection traces with minimal manual post-processing. We present an interactive design interface for users to customize KnitUI’s colors, sizes, positions, and shapes. After investigating design parameters for the optimized sensing and interactive performance, we demonstrate KnitUI as a portable, deformable, washable, and customizable interactive and sensing platform. It obtains diverse applications, including wearable user interfaces, tactile sensing wearables, and artificial robot skin.

The reflectance field of a face describes the reflectance properties responsible for complex lighting effects including diffuse, specular, inter-reflection and self shadowing. Most existing methods for estimating the face reflectance from a monocular image assume faces to be diffuse with very few approaches adding a specular component. This still leaves out important perceptual aspects of reflectance such as higher-order global illumination effects and self-shadowing. We present a new neural representation for face reflectance where we can estimate all components of the reflectance responsible for the final appearance from a monocular image. Instead of modeling each component of the reflectance separately using parametric models, our neural representation allows us to generate a basis set of faces in a geometric deformation-invariant space, parameterized by the input light direction, viewpoint and face geometry. We learn to reconstruct this reflectance field of a face just from a monocular image, which can be used to render the face from any viewpoint in any light condition. Our method is trained on a light-stage dataset, which captures 300 people illuminated with 150 light conditions from 8 viewpoints. We show that our method outperforms existing monocular reflectance reconstruction methods due to better capturing of physical effects, such as sub-surface scattering, specularities, self-shadows and other higher-order effects.

Daily human activities, e.g., locomotion, exercises, and resting, are heavily guided by the tactile interactions between the human and the ground. In this work, leveraging such tactile interactions, we propose a 3D human pose estimation approach using the pressure maps recorded by a tactile carpet as input. We build a low-cost, high-density, large-scale intelligent carpet, which enables the real-time recordings of human-floor tactile interactions in a seamless manner. We collect a synchronized tactile and visual dataset on various human activities. Employing a state-of-the-art camera-based pose estimation model as supervision, we design and implement a deep neural network model to infer 3D human poses using only the tactile information. Our pipeline can be further scaled up to multi-person pose estimation. We evaluate our system and demonstrate its potential applications in diverse fields.

We present methods for co-designing rigid robots over control and morphology (including discrete topology) over multiple objectives. Previous work has addressed problems in single-objective robot co-design or multi-objective control. However, the joint multi-objective co-design problem is extremely important for generating capable, versatile, algorithmically designed robots. In this work, we present Multi-Objective Graph Heuristic Search, which extends a single-objective graph heuristic search from previous work to enable a highly efficient multi-objective search in a combinatorial design topology space. Core to this approach, we introduce a new universal, multiobjective heuristic function based on graph neural networks that is able to effectively leverage learned information between different task trade-offs. We demonstrate our approach on six combinations of seven terrestrial locomotion and design tasks, including one three-objective example. We compare the captured Pareto fronts across different methods and demonstrate that our multi-objective graph heuristic search quantitatively and qualitatively outperforms other techniques.

Tactile sensing is critical for humans to perform everyday tasks. While significant progress has been made in analyzing object grasping from vision, it remains unclear how we can utilize tactile sensing to reason about and model the dynamics of hand-object interactions. In this work, we employ a high-resolution tactile glove to perform four different interactive activities on a diversified set of objects. We propose a framework aiming at predicting the 3d locations of both the hand and the object purely from the touch data by combining a predictive model and a contrastive learning module. This framework can reason about the interaction patterns from the tactile data, hallucinate the changes in the environment, esti-mate the uncertainty of the prediction, and generalize to unseen objects. We also provide detailed ablation studies regarding different system designs as well as visualizations of the predicted trajectories. This work takes a step on dynamics modeling in hand-object interactions from dense tactile sensing, which opens the door for future applications in activity learning, human-computer interactions, and imitation learning for robotics.

Both the design and control of a robot play equally important roles in its task performance. However, while optimal control is well studied in the machine learning and robotics community, less attention is placed on finding the optimal robot design. This is mainly because co-optimizing design and control in robotics is characterized as a challenging problem, and more importantly, a comprehensive evaluation benchmark for co-optimization does not exist. In this paper, we propose Evolution Gym, the first large-scale benchmark for co-optimizing the design and control of soft robots. In our benchmark, each robot is composed of different types of voxels (e.g., soft, rigid, actuators), resulting in a modular and expressive robot design space. Our benchmark environments span a wide range of tasks, including locomotion on various types of terrains and manipulation. Furthermore, we develop several robot co-evolution algorithms by combining state-of-the-art design optimization methods and deep reinforcement learning techniques. Evaluating the algorithms on our benchmark platform, we observe robots exhibiting increasingly complex behaviors as evolution progresses, with the best evolved designs solving many of our proposed tasks. Additionally, even though robot designs are evolved autonomously from scratch without prior knowledge, they often grow to resemble existing natural creatures while outperforming hand-designed robots. Nevertheless, all tested algorithms fail to find robots that succeed in our hardest environments. This suggests that more advanced algorithms are required to explore the high-dimensional design space and evolve increasingly intelligent robots -- an area of research in which we hope Evolution Gym will accelerate progress. Our website with code, environments, documentation, and tutorials is available at http://evogym.csail.mit.edu/.

Photorealistic editing of head portraits is a challenging task as humans are very sensitive to inconsistencies in faces. We present an approach for high-quality intuitive editing of the camera viewpoint and scene illumination (parameterised with an environment map) in a portrait image. This requires our method to capture and control the full reflectance field of the person in the image. Most editing approaches rely on supervised learning using training data captured with setups such as light and camera stages. Such datasets are expensive to acquire, not readily available and do not capture all the rich variations of in-the-wild portrait images. In addition, most supervised approaches only focus on relighting, and do not allow camera viewpoint editing. Thus, they only capture and control a subset of the reflectance field. Recently, portrait editing has been demonstrated by operating in the generative model space of StyleGAN. While such approaches do not require direct supervision, there is a significant loss of quality when compared to the supervised approaches. In this paper, we present a method which learns from limited supervised training data. The training images only include people in a fixed neutral expression with eyes closed, without much hair or background variations. Each person is captured under 150 one-light-at-a-time conditions and under 8 camera poses. Instead of training directly in the image space, we design a supervised problem which learns transformations in the latent space of StyleGAN. This combines the best of supervised learning and generative adversarial modeling. We show that the StyleGAN prior allows for generalisation to different expressions, hairstyles and backgrounds. This produces high-quality photorealistic results for in-the-wild images and significantly outperforms existing methods. Our approach can edit the illumination and pose simultaneously, and runs at interactive rates.

The computational design of soft underwater swimmers is challenging because of the high degrees of freedom in soft-body modeling. In this paper, we present a differentiable pipeline for co-designing a soft swimmer's geometry and controller. Our pipeline unlocks gradient-based algorithms for discovering novel swimmer designs more efficiently than traditional gradient-free solutions. We propose Wasserstein barycenters as a basis for the geometric design of soft underwater swimmers since it is differentiable and can naturally interpolate between bio-inspired base shapes via optimal transport. By combining this design space with differentiable simulation and control, we can efficiently optimize a soft underwater swimmer's performance with fewer simulations than baseline methods. We demonstrate the efficacy of our method on various design problems such as fast, stable, and energy-efficient swimming and demonstrate applicability to multi-objective design.

We present a novel workflow to design and program knitted garments for industrial whole-garment knitting machines. Inspired by traditional garment making based on cutting and sewing, we propose a sketch representation with additional annotations necessary to model the knitting process. Our system bypasses complex editing operations in 3D space, which allows us to achieve interactive editing of both the garment shape and its underlying time process. We provide control of the local knitting direction, the location of important course interfaces, as well as the placement of stitch irregularities that form seams in the final garment. After solving for the constrained knitting time process, the garment sketches are automatically segmented into a minimal set of simple regions that can be knitted using simple knitting procedures. Finally, our system optimizes a stitch graph hierarchically while providing control over the tradeoff between accuracy and simplicity. We showcase different garments created with our web interface.

Manufactured parts are meticulously engineered to perform well with respect to several conflicting metrics, like weight, stress, and cost. The best achievable trade-offs reside on the Pareto front , which can be discovered via performance-driven optimization. The objectives that define this Pareto front often incorporate assumptions about the context in which a part will be used, including loading conditions, environmental influences, material properties, or regions that must be preserved to interface with a surrounding assembly. Existing multi-objective optimization tools are only equipped to study one context at a time, so engineers must run independent optimizations for each context of interest. However, engineered parts frequently appear in many contexts: wind turbines must perform well in many wind speeds, and a bracket might be optimized several times with its bolt-holes fixed in different locations on each run. In this paper, we formulate a framework for variable-context multi-objective optimization. We introduce the Pareto gamut , which captures Pareto fronts over a range of contexts. We develop a global/local optimization algorithm to discover the Pareto gamut directly, rather than discovering a single fixed-context "slice" at a time. To validate our method, we adapt existing multi-objective optimization benchmarks to contextual scenarios. We also demonstrate the practical utility of Pareto gamut exploration for several engineering design problems.

Parametric computer-aided design (CAD) is a standard paradigm used to design manufactured objects, where a 3D shape is represented as a program supported by the CAD software. Despite the pervasiveness of parametric CAD and a growing interest from the research community, currently there does not exist a dataset of realistic CAD models in a concise programmatic form. In this paper we present the Fusion 360 Gallery , consisting of a simple language with just the sketch and extrude modeling operations, and a dataset of 8,625 human design sequences expressed in this language. We also present an interactive environment called the Fusion 360 Gym , which exposes the sequential construction of a CAD program as a Markov decision process, making it amendable to machine learning approaches. As a use case for our dataset and environment, we define the CAD reconstruction task of recovering a CAD program from a target geometry. We report results of applying state-of-the-art methods of program synthesis with neurally guided search on this task.

Tasks in multi-task learning often correlate, conflict, or even compete with each other. As a result, a single solution that is optimal for all tasks rarely exists. Recent papers introduced the concept of Pareto optimality to this field and directly cast multi-task learning as multi-objective optimization problems, but solutions returned by existing methods are typically finite, sparse, and discrete. We present a novel, efficient method that generates locally continuous Pareto sets and Pareto fronts, which opens up the possibility of continuous analysis of Pareto optimal solutions in machine learning problems. We scale up theoretical results in multi-objective optimization to modern machine learning problems by proposing a sample-based sparse linear system, for which standard Hessian-free solvers in machine learning can be applied. We compare our method to the state-of-the-art algorithms and demonstrate its usage of analyzing local Pareto sets on various multi-task classification and regression problems. The experimental results confirm that our algorithm reveals the primary directions in local Pareto sets for trade-off balancing, finds more solutions with different trade-offs efficiently, and scales well to tasks with millions of parameters.

Many real-world control problems involve conflicting objectives where we desire a dense and high-quality set of control policies that are optimal for different objective preferences (called Pareto-optimal). While extensive research in multi-objective reinforcement learning (MORL) has been conducted to tackle such problems, multi-objective optimization for complex continuous robot control is still under-explored. In this work, we propose an efficient evolutionary learning algorithm to find the Pareto set approximation for continuous robot control problems, by extending a state-of-the-art RL algorithm and presenting a novel prediction model to guide the learning process. In addition to efficiently discovering the individual policies on the Pareto front, we construct a continuous set of Pareto-optimal solutions by Pareto analysis and interpolation. Furthermore, we design seven multi-objective RL environments with continuous action space, which is the first benchmark platform to evaluate MORL algorithms on various robot control problems. We test the previous methods on the proposed benchmark problems, and the experiments show that our approach is able to find a much denser and higher-quality set of Pareto policies than the existing algorithms.

Many science, engineering, and design optimization problems require balancing the trade-offs between several conflicting objectives. The objectives are often black-box functions whose evaluations are time-consuming and costly. Multi-objective Bayesian optimization can be used to automate the process of discovering the set of optimal solutions, called Pareto-optimal, while minimizing the number of performed evaluations. To further reduce the evaluation time in the optimization process, testing of several samples in parallel can be deployed. We propose a novel multi-objective Bayesian optimization algorithm that iteratively selects the best batch of samples to be evaluated in parallel. Our algorithm approximates and analyzes a piecewise-continuous Pareto set representation. This representation allows us to introduce a batch selection strategy that optimizes for both hypervolume improvement and diversity of selected samples in order to efficiently advance promising regions of the Pareto front. Experiments on both synthetic test functions and real-world benchmark problems show that our algorithm predominantly outperforms relevant state-of-the-art methods. Code is available at https://github.com/yunshengtian/DGEMO.

Black-box topology optimization (BBTO) uses evolutionary algorithms and other soft computing techniques to generate near-optimal topologies of mechanical structures. Although evolutionary algorithms are widely used to compensate the limited applicability of conventional gradient optimization techniques, methods based on BBTO have been criticized due to numerous drawbacks. In this article, we discuss topology optimization as a black-box optimization problem. We review the main BBTO methods, discuss their challenges and present approaches to relax them. Dealing with those challenges effectively can lead to wider applicability of topology optimization, as well as the ability to tackle industrial, highly constrained, nonlinear, many-objective, and multimodal problems. Consequently, future research in this area may open the door for innovating new applications in science and engineering that may go beyond solving classical optimization problems of mechanical structures. Furthermore, algorithms designed for BBTO can be added to existing software toolboxes and packages of topology optimization.

We present a method for performance-driven optimization of fluidic devices. In our approach, engineers provide a high-level specification of a device using parametric surfaces for the fluid-solid boundaries. They also specify desired flow properties for inlets and outlets of the device. Our computational approach optimizes the boundary of the fluidic device such that its steady-state flow matches desired flow at outlets. In order to deal with computational challenges of this task, we propose an efficient, differentiable Stokes flow solver. Our solver provides explicit access to gradients of performance metrics with respect to the parametric boundary representation. This key feature allows us to couple the solver with efficient gradient-based optimization methods. We demonstrate the efficacy of this approach on designs of five complex 3D fluidic systems. Our approach makes an important step towards practical computational design tools for high-performance fluidic devices.

3D printing technology is a powerful tool for manufacturing complex shapes with high-quality textures. Gloss, next to color and shape, is one of the most salient visual aspects of an object. Unfortunately, printing a wide range of spatially-varying gloss properties using state-of-the-art 3D printers is challenging as it relies on geometrical modifications to achieve the desired appearance. A common post-processing step is to apply off-the-shelf varnishes that modify the final gloss. The main difficulty in automating this process lies in the physical properties of the varnishes which owe their appearance to a high concentration of large particles and as such, they cannot be easily deposited with current 3D color printers. As a result, fine-grained control of gloss properties using today's 3D printing technologies is limited in terms of both spatial resolution and the range of achievable gloss. We address the above limitations and propose new printing hardware based on piezo-actuated needle valves capable of jetting highly viscous varnishes. Based on the new hardware setup, we present the complete pipeline for controlling the gloss of a given 2.5 D object, from printer calibration, through material selection, to the manufacturing of models with spatially-varying reflectance. Furthermore, we discuss the potential integration with current 3D printing technology. Apart from being a viable solution for 3D printing, our method offers an additional and essential benefit of separating color and gloss fabrication which makes the process more flexible and enables high-quality color and gloss reproduction.

We present MATch , a method to automatically convert photographs of material samples into production-grade procedural material models. At the core of MATch is a new library DiffMat that provides differentiable building blocks for constructing procedural materials, and automatic translation of large-scale procedural models, with hundreds to thousands of node parameters, into differentiable node graphs. Combining these translated node graphs with a rendering layer yields an end-to-end differentiable pipeline that maps node graph parameters to rendered images. This facilitates the use of gradient-based optimization to estimate the parameters such that the resulting material, when rendered, matches the target image appearance, as quantified by a style transfer loss. In addition, we propose a deep neural feature-based graph selection and parameter initialization method that efficiently scales to a large number of procedural graphs. We evaluate our method on both rendered synthetic materials and real materials captured as flash photographs. We demonstrate that MATch can reconstruct more accurate, general, and complex procedural materials compared to the state-of-the-art. Moreover, by producing a procedural output, we unlock capabilities such as constructing arbitrary-resolution material maps and parametrically editing the material appearance.

We present RoboGrammar , a fully automated approach for generating optimized robot structures to traverse given terrains. In this framework, we represent each robot design as a graph, and use a graph grammar to express possible arrangements of physical robot assemblies. Each robot design can then be expressed as a sequence of grammar rules. Using only a small set of rules our grammar can describe hundreds of thousands of possible robot designs. The construction of the grammar limits the design space to designs that can be fabricated. For a given input terrain, the design space is searched to find the top performing robots and their corresponding controllers. We introduce Graph Heuristic Search - a novel method for efficient search of combinatorial design spaces. In Graph Heuristic Search, we explore the design space while simultaneously learning a function that maps incomplete designs (e.g., nodes in the combinatorial search tree) to the best performance values that can be achieved by expanding these incomplete designs. Graph Heuristic Search prioritizes exploration of the most promising branches of the design space. To test our method we optimize robots for a number of challenging and varied terrains. We demonstrate that RoboGrammar can successfully generate nontrivial robots that are optimized for a single terrain or a combination of terrains.

How much can we infer about a person’s looks from the way they speak? In this paper, we study the task of reconstructing a facial image of a person from a short audio recording of that person speaking. We design and train a deep neural network to perform this task using millions of natural Internet/Youtube videos of people speaking. During training, our model learns voice-face correlations that allow it to produce images that capture various physical attributes of the speakers such as age, gender and ethnicity. This is done in a self-supervised manner, by utilizing the natural co-occurrence of faces and speech in Internet videos, without the need to model attributes explicitly. We evaluate and numerically quantify how–-and in what manner–-our Speech2Face reconstructions, obtained directly from audio, resemble the true face images of the speakers.

Understanding where people are looking is an informative social cue. In this work, we present Gaze360, a large-scale remote gaze-tracking dataset and method for robust 3D gaze estimation in unconstrained images. Our dataset consists of 238 subjects in indoor and outdoor environments with labelled 3D gaze across a wide range of head poses and distances. It is the largest publicly available dataset of its kind by both subject and variety, made possible by a simple and efficient collection method. Our proposed 3D gaze model extends existing models to include temporal information and to directly output an estimate of gaze uncertainty. We demonstrate the benefits of our model via an ablation study, and show its generalization performance via a cross-dataset evaluation against other recent gaze benchmark datasets. We furthermore propose a simple self-supervised approach to improve cross-dataset domain adaptation. Finally, we demonstrate an application of our model for estimating customer attention in a supermarket setting. Our dataset and models will be made available at http://gaze360.csail.mit.edu.

Motivated by the recent potential of mass customization brought by whole-garment knitting machines, we introduce the new problem of automatic machine instruction generation using a single image of the desired physical product, which we apply to machine knitting. We propose to tackle this problem by directly learning to synthesize regular machine instructions from real images. We create a cured dataset of real samples with their instruction counterpart and propose to use synthetic images to augment it in a novel way. We theoretically motivate our data mixing framework and show empirical results suggesting that making real images look more synthetic is beneficial in our problem setup.

Physical simulators have been widely used in robot planning and control. Among them, differentiable simulators are particularly favored, as they can be incorporated into gradient-based optimization algorithms that are efficient in solving inverse problems such as optimal control and motion planning. Therefore, rigid body simulators and recently their differentiable variants are studied extensively. Simulating deformable objects is, however, more challenging compared to rigid body dynamics. The underlying physical laws of deformable objects are more complex, and the resulting systems have orders of magnitude more degrees of freedom and there-fore they are significantly more computationally expensive to simulate. Computing gradients with respect to physical design or controller parameters is typically even more computationally challenging. In this paper, we propose a real-time, differentiable hybrid Lagrangian-Eulerian physical simulator for deformable objects, ChainQueen, based on the Moving Least Squares Material Point Method (MLS-MPM). MLS-MPM can simulate deformable objects with collisions and can be seamlessly incorporated into soft robotic systems. We demonstrate that our simulator achieves high precision in both forward simulation and backward gradient computation. We have successfully employed it in a diverse set of inference, control and co-design tasks for soft robotics.

Soft robots have continuum solid bodies that can deform in an infinite number of ways. Controlling soft robots is very challenging as there are no closed form solutions. We present a learning-in-the-loop co-optimization algorithm in which a latent state representation is learned as the robot figures out how to solve the task. Our solution marries hybrid particle-grid-based simulation with deep, variational convolutional autoencoder architectures that can capture salient features of robot dynamics with high efficacy. We demonstrate our dynamics-aware feature learning algorithm on both 2D and 3D soft robots, and show that it is more robust and faster converging than the dynamics-oblivious baseline. We validate the behavior of our algorithm with visualizations of the learned representation.

This work presents a novel interactive system for simple garment composition and surface patterning. Our approach makes it easier for casual users to customize machine-knitted garments, while enabling more advanced users to design their own composable templates. Our tool combines ideas from CAD software and image editing: it allows the composition of (1) parametric knitted primitives, and (2) stitch pattern layers with different resampling behaviours. By leveraging the regularity of our primitives, our tool enables interactive customization with automated layout and real-time patterning feedback. We show a variety of garments and patterns created with our tool, and highlight our ability to transfer shape and pattern customizations between users.

Hybrid unmanned aerial vehicles (UAV) combine advantages of multicopters and fixed-wing planes: vertical take-off, landing, and low energy use. However, hybrid UAVs are rarely used because controller design is challenging due to its complex, mixed dynamics. In this paper, we propose a method to automate this design process by training a mode-free, model-agnostic neural network controller for hybrid UAVs. We present a neural network controller design with a novel error convolution input trained by reinforcement learning. Our controller exhibits two key features: First, it does not distinguish among flying modes, and the same controller structure can be used for copters with various dynamics. Second, our controller works for real models without any additional parameter tuning process, closing the gap between virtual simulation and real fabrication. We demonstrate the efficacy of the proposed controller both in simulation and in our custom-built hybrid UAVs (Figure 1, 8). The experiments show that the controller is robust to exploit the complex dynamics when both rotors and wings are active in flight tests.

In this work, we propose two ensemble methods leveraging a crowd workforce to improve video annotation, with a focus on video object segmentation. Their shared principle is that while individual candidate results may likely be insufficient, they often complement each other so that they can be combined into something better than any of the individual results---the very spirit of collaborative working. For one, we extend a standard polygon-drawing interface to allow workers to annotate negative space, and combine the work of multiple workers instead of relying on a single best one as commonly done in crowdsourced image segmentation. For the other, we present a method to combine multiple automatic propagation algorithms with the help of the crowd. Such combination requires an understanding of where the algorithms fail, which we gather using a novel coarse scribble video annotation task. We evaluate our ensemble methods, discuss our design choices for them, and make our web-based crowdsourcing tools and results publicly available.

Despite the ubiquity of carpentered items, the customization of carpentered items remains labor intensive. The generation of laymen editable templates for carpentry is difficult. Current design tools rely heavily on CNC fabrication, limiting applicability. We develop a template based system for carpentry and a robotic fabrication system using mobile robots and standard carpentry tools. Our end-to-end design and fabrication tool democratizes design and fabrication of carpentered items. Our method combines expert knowledge for template design, allows laymen users to customize and verify specific designs, and uses robotics system to fabricate parts. We validate our system using multiple designs to make customizable, verifiable templates and fabrication plans and show an end-to-end example that was designed, manufactured, and assembled using our tools.

A wide adoption of 3-D videos is hindered by the lack of high-quality 3-D content. One promising solution to this problem is through data-driven 2-D-to-3-D video conversion. Such approaches are based on learning depth maps from a large dataset of 2-D+Depth images. However, current conversion methods, while general, produce low-quality results with artifacts that are not acceptable to many viewers. We propose a novel, data-driven method for 2-D-to-3-D video conversion. Our method transfers the depth gradients from a large database of 2-D+Depth images. Capturing 2-D+Depth databases, however, are complex and costly, especially for outdoor sports games. We address this problem by creating a synthetic database from computer games and showing that this synthetic database can effectively be used to convert real videos. We propose a spatio-temporal method to ensure the smoothness of the generated depth within individual frames and across successive frames. In addition, we present an object boundary detection method customized for 2-D-to-3-D conversion systems, which produces clear depth boundaries for players. We implement our method and validate it by conducting user studies that evaluate depth perception and visual comfort of the converted 3-D videos. We show that our method produces high-quality 3-D videos that are almost indistinguishable from videos shot by stereo cameras. In addition, our method significantly outperforms the current state-of-the-art methods. For example, up to 20% improvement in the perceived depth is achieved by our method, which translates to improving the mean opinion score from good to excellent.

Accurate representation of soft transitions between image regions is essential for high-quality image editing and compositing. Current techniques for generating such representations depend heavily on interaction by a skilled visual artist, as creating such accurate object selections is a tedious task. In this work, we introduce semantic soft segments , a set of layers that correspond to semantically meaningful regions in an image with accurate soft transitions between different objects. We approach this problem from a spectral segmentation angle and propose a graph structure that embeds texture and color features from the image as well as higher-level semantic information generated by a neural network. The soft segments are generated via eigendecomposition of the carefully constructed Laplacian matrix fully automatically. We demonstrate that otherwise complex image editing tasks can be done with little effort using semantic soft segments.

While computer-aided design is a major part of many modern manufacturing pipelines, the design files typically generated describe raw geometry. Lost in this representation is the procedure by which these designs were generated. In this paper, we present a method for reverse-engineering the process by which 3D models may have been generated, in the language of constructive solid geometry (CSG). Observing that CSG is a formal grammar, we formulate this inverse CSG problem as a program synthesis problem. Our solution is an algorithm that couples geometric processing with state-of-the-art program synthesis techniques. In this scheme, geometric processing is used to convert the mixed discrete and continuous domain of CSG trees to a pure discrete domain where modern program synthesizers excel. We demonstrate the efficiency and scalability of our algorithm on several different examples, including those with over 100 primitive parts. We show that our algorithm is able to find simple programs which are close to the ground truth, and demonstrate our method's applicability in mesh re-editing. Finally, we compare our method to prior state-of-the-art. We demonstrate that our algorithm dominates previous methods in terms of resulting CSG compactness and runtime, and can handle far more complex input meshes than any previous method.

A variety of structures in nature exhibit sparse, thin, and intricate features. It is challenging to investigate these structural characteristics using conventional numerical approaches since such features require highly refined spatial resolution to capture and therefore they incur a prohibitively high computational cost. We present a novel computational framework for high-resolution topology optimization that delivers leaps in simulation capabilities, by two orders of magnitude, from the state-of-the-art approaches. Our technique accommodates computational domains with over one billion grid voxels on a single shared-memory multiprocessor platform, allowing automated emergence of structures with both rich geometric features and exceptional mechanical performance. To achieve this, we track the evolution of thin structures and simulate its elastic deformation in a dynamic narrow-band region around high-density sites to avoid wasted computational effort on large void regions. We have also designed a mixed-precision multigrid-preconditioned iterative solver that keeps the memory footprint of the simulation to a compact size while maintaining double-precision accuracy. We have demonstrated the efficacy of the algorithm through optimizing a variety of complex structures from both natural and engineering systems.

Typical design for manufacturing applications requires simultaneous optimization of conflicting performance objectives: Design variations that improve one performance metric may decrease another performance metric. In these scenarios, there is no unique optimal design but rather a set of designs that are optimal for different trade-offs (called Pareto-optimal). In this work, we propose a novel approach to discover the Pareto front, allowing designers to navigate the landscape of compromises efficiently. Our approach is based on a first-order approximation of the Pareto front, which allows entire neighborhoods rather than individual points on the Pareto front to be captured. In addition to allowing for efficient discovery of the Pareto front and the corresponding mapping to the design space, this approach allows us to represent the entire trade-off manifold as a small collection of patches that comprise a high-quality and piecewise-smooth approximation. We illustrate how this technique can be used for navigating performance trade-offs in computer-aided design (CAD) models.

We propose a workflow for spectral reproduction of paintings, which captures a painting's spectral color, invariant to illumination, and reproduces it using multi-material 3D printing. We take advantage of the current 3D printers' capabilities of combining highly concentrated inks with a large number of layers, to expand the spectral gamut of a set of inks. We use a data-driven method to both predict the spectrum of a printed ink stack and optimize for the stack layout that best matches a target spectrum. This bidirectional mapping is modeled using a pair of neural networks, which are optimized through a problem-specific multi-objective loss function. Our loss function helps find the best possible ink layout resulting in the balance between spectral reproduction and colorimetric accuracy under a multitude of illuminants. In addition, we introduce a novel spectral vector error diffusion algorithm based on combining color contoning and halftoning, which simultaneously solves the layout discretization and color quantization problems, accurately and efficiently. Our workflow outperforms the state-of-the-art models for spectral prediction and layout optimization. We demonstrate reproduction of a number of real paintings and historically important pigments using our prototype implementation that uses 10 custom inks with varying spectra and a resin-based 3D printer.

Reflections can obstruct content during video capture and hence their removal is desirable. Current removal techniques are designed for still images, extracting only one reflection (foreground) and one background layer from the input. When extended to videos, unpleasant artifacts such as temporal flickering and incomplete separation are generated. We present a technique for video reflection removal by jointly solving for motion and separation. The novelty of our work is in our optimization formulation as well as the motion initialization strategy. We present a novel spatiotemporal optimization that takes n frames as input and directly estimates 2n frames as output, n for each layer. We aim to fully utilize spatio-temporal information in our objective terms. Our motion initialization is based on iterative frame-to-frame alignment instead of the direct alignment used by current approaches. We compare against advanced video extensions of the state of the art, and we significantly reduce temporal flickering and improve separation. In addition, we reduce image blur and recover moving objects more accurately. We validate our approach through subjective and objective evaluations on real and controlled data.

Appearance reproduction is an important aspect of 3D printing. Current color reproduction systems use halftoning methods that create colors through a spatial combination of different inks at the object's surface. This introduces a variety of artifacts to the object, especially when viewed from a closer distance. In this work, we propose an alternative color reproduction method for 3D printing. Inspired by the inherent ability of 3D printers to layer different materials on top of each other, 3D color contoning creates colors by combining inks with various thicknesses inside the object's volume. Since inks are inside the volume, our technique results in a uniform color surface with virtually invisible spatial patterns on the surface. For color prediction, we introduce a simple and highly accurate spectral model that relies on a weighted regression of spectral absorptions. We fully characterize the proposed framework by addressing a number of problems, such as material arrangement, calculation of ink concentration, and 3D dot gain. We use a custom 3D printer to fabricate and validate our results.

The realistic simulation of highly-dynamic elastic objects is important for a broad range of applications in computer graphics, engineering and computational fabrication. However, whether simulating flipping toys, jumping robots, prosthetics or quickly moving creatures, performing such simulations in the presence of contact, impact and friction is both time consuming and inaccurate. In this paper we present Dynamics-Aware Coarsening (DAC) and the Boundary Balanced Impact (BBI) model which allow for the accurate simulation of dynamic, elastic objects undergoing both large scale deformation and frictional contact, at rates up to 79 times faster than state-of-the-art methods. DAC and BBI produce simulations that are accurate and fast enough to be used (for the first time) for the computational design of 3D-printable compliant dynamic mechanisms. Thus we demonstrate the efficacy of DAC and BBI by designing and fabricating mechanisms which flip, throw and jump over and onto obstacles as requested.

Stereoscopic 3D (S3D) movies have become widely popular in the movie theaters, but the adoption of S3D at home is low even though most TV sets support S3D. It is widely believed that S3D with glasses is not the right approach for the home. A much more appealing approach is to use automulti-scopic displays that provide a glasses-free 3D experience to multiple viewers. A technical challenge is the lack of native multiview content that is required to deliver a proper view of the scene for every viewpoint. Our approach takes advantage of the abundance of stereoscopic 3D movies. We propose a real-time system that can convert stereoscopic video to a high-quality multiview video that can be directly fed to automultiscopic displays. Our algorithm uses a wavelet-based decomposition of stereoscopic images with per-wavelet disparity estimation. A key to our solution lies in combining Lagrangian and Eulerian approaches for both the disparity estimation and novel view synthesis, which leverages the complementary advantages of both techniques. The solution preserves all the features of Eulerian methods, e.g., subpixel accuracy, high performance, robustness to ambiguous depth cases, and easy integration of inter-view aliasing while maintaining the advantages of Lagrangian approaches, e.g., robustness to large disparities and possibility of performing non-trivial disparity manipulations through both view extrapolation and interpolation. The method achieves real-time performance on current GPUs. Its design also enables an easy hardware implementation that is demonstrated using a field-programmable gate array. We analyze the visual quality and robustness of our technique on a number of synthetic and real-world examples. We also perform a user experiment which demonstrates benefits of the technique when compared to existing solutions.

While collections of parametric shapes are growing in size and use, little progress has been made on the fundamental problem of shape-based matching and retrieval for parametric shapes in a collection. The search space for such collections is both discrete (number of shapes) and continuous (parameter values). In this work, we propose representing this space using descriptors that have shown to be effective for single shape retrieval. While single shapes can be represented as points in a descriptor space, parametric shapes are mapped into larger continuous regions. For smooth descriptors, we can assume that these regions are bounded low-dimensional manifolds where the dimensionality is given by the number of shape parameters. We propose representing these manifolds with a set of primitives, namely, points and bounded tangent spaces. Our algorithm describes how to define these primitives and how to use them to construct a manifold approximation that allows accurate and fast retrieval. We perform an analysis based on curvature, boundary evaluation, and the allowed approximation error to select between primitive types. We show how to compute decision variables with no need for empirical parameter adjustments and discuss theoretical guarantees on retrieval accuracy. We validate our approach with experiments that use different types of descriptors on a collection of shapes from multiple categories.

Computer Aided Design (CAD) is a multi-billion dollar industry used by almost every mechanical engineer in the world to create practically every existing manufactured shape. CAD models are not only widely available but also extremely useful in the growing field of fabrication-oriented design because they are parametric by construction and capture the engineer's design intent, including manufacturability. Harnessing this data, however, is challenging, because generating the geometry for a given parameter value requires time-consuming computations. Furthermore, the resulting meshes have different combinatorics, making the mesh data inherently discontinuous with respect to parameter adjustments. In our work, we address these challenges and develop tools that allow interactive exploration and optimization of parametric CAD data. To achieve interactive rates, we use precomputation on an adaptively sampled grid and propose a novel scheme for interpolating in this domain where each sample is a mesh with different combinatorics. Specifically, we extract partial correspondences from CAD representations for local mesh morphing and propose a novel interpolation method for adaptive grids that is both continuous/smooth and local (i.e., the influence of each sample is constrained to the local regions where mesh morphing can be computed). We show examples of how our method can be used to interactively visualize and optimize objects with a variety of physical properties.

Holograms display a 3D image in high resolution and allow viewers to focus freely as if looking through a virtual window, yet computer generated holography (CGH) hasn't delivered the same visual quality under plane wave illumination and due to heavy computational cost. Light field displays have been popular due to their capability to provide continuous focus cues. However, light field displays must trade off between spatial and angular resolution, and do not model diffraction. We present a light field-based CGH rendering pipeline allowing for reproduction of high-definition 3D scenes with continuous depth and support of intra-pupil view-dependent occlusion. Our rendering accurately accounts for diffraction and supports various types of reference illuminations for hologram. We avoid under- and over-sampling and geometric clipping effects seen in previous work. We also demonstrate an implementation of light field rendering plus the Fresnel diffraction integral based CGH calculation which is orders of magnitude faster than the state of the art [Zhang et al. 2015], achieving interactive volumetric 3D graphics. To verify our computational results, we build a see-through, near-eye, color CGH display prototype which enables co-modulation of both amplitude and phase. We show that our rendering accurately models the spherical illumination introduced by the eye piece and produces the desired 3D imagery at the designated depth. We also analyze aliasing, theoretical resolution limits, depth of field, and other design trade-offs for near-eye CGH.

In this paper we present a novel two-scale framework to optimize the structure and the material distribution of an object given its functional specifications. Our approach utilizes multi-material microstructures as low-level building blocks of the object. We start by precomputing the material property gamut -- the set of bulk material properties that can be achieved with all material microstructures of a given size. We represent the boundary of this material property gamut using a level set field. Next, we propose an efficient and general topology optimization algorithm that simultaneously computes an optimal object topology and spatially-varying material properties constrained by the precomputed gamut. Finally, we map the optimal spatially-varying material properties onto the microstructures with the corresponding properties in order to generate a high-resolution printable structure. We demonstrate the efficacy of our framework by designing, optimizing, and fabricating objects in different material property spaces on the level of a trillion voxels, i.e several orders of magnitude higher than what can be achieved with current systems.

In this article, we present a novel two-scale framework to optimize the structure and the material distribution of an object given its functional specifications. Our approach utilizes multi-material microstructures as low-level building blocks of the object. We start by precomputing the material property gamut—the set of bulk material properties that can be achieved with all material microstructures of a given size. We represent the boundary of this material property gamut using a level set field. Next, we propose an efficient and general topology optimization algorithm that simultaneously computes an optimal object topology and spatially varying material properties constrained by the precomputed gamut. Finally, we map the optimal spatially varying material properties onto the microstructures with the corresponding properties to generate a high-resolution printable structure. We demonstrate the efficacy of our framework by designing, optimizing, and fabricating objects in different material property spaces on the level of a trillion voxels, that is, several orders of magnitude higher than what can be achieved with current systems.

From scientific research to commercial applications, eye tracking is an important tool across many domains. Despite its range of applications, eye tracking has yet to become a pervasive technology. We believe that we can put the power of eye tracking in everyone's palm by building eye tracking software that works on commodity hardware such as mobile phones and tablets, without the need for additional sensors or devices. We tackle this problem by introducing GazeCapture, the first large-scale dataset for eye tracking, containing data from over 1450 people consisting of almost 2:5M frames. Using GazeCapture, we train iTracker, a convolutional neural network for eye tracking, which achieves a significant reduction in error over previous approaches while running in real time (10-15fps) on a modern mobile device. Our model achieves a prediction error of 1.71cm and 2.53cm without calibration on mobile phones and tablets respectively. With calibration, this is reduced to 1.34cm and 2.12cm. Further, we demonstrate that the features learned by iTracker generalize well to other datasets, achieving state-of-the-art results. The code, data, and models are available at http://gazecapture.csail.mit.edu.

We demonstrate a new approach for designing functional material definitions for multi-material fabrication using our system called Foundry. Foundry provides an interactive and visual process for hierarchically designing spatially-varying material properties (e.g., appearance, mechanical, optical). The resulting meta-materials exhibit structure at the micro and macro level and can surpass the qualities of traditional composites. The material definitions are created by composing a set of operators into an operator graph. Each operator performs a volume decomposition operation, remaps space, or constructs and assigns a material composition. The operators are implemented using a domain-specific language for multi-material fabrication; users can easily extend the library by writing their own operators. Foundry can be used to build operator graphs that describe complex, parameterized, resolution-independent, and reusable material definitions. We also describe how to stage the evaluation of the final material definition which in conjunction with progressive refinement, allows for interactive material evaluation even for complex designs. We show sophisticated and functional parts designed with our system.

With existing programming tools, writing high-performance simulation code is labor intensive and requires sacrificing readability and portability. The alternative is to prototype simulations in a high-level language like Matlab, thereby sacrificing performance. The Matlab programming model naturally describes the behavior of an entire physical system using the language of linear algebra. However, simulations also manipulate individual geometric elements, which are best represented using linked data structures like meshes. Translating between the linked data structures and linear algebra comes at significant cost, both to the programmer and to the machine. High-performance implementations avoid the cost by rephrasing the computation in terms of linked or index data structures, leaving the code complicated and monolithic, often increasing its size by an order of magnitude. In this article, we present Simit, a new language for physical simulations that lets the programmer view the system both as a linked data structure in the form of a hypergraph and as a set of global vectors, matrices, and tensors depending on what is convenient at any given time. Simit provides a novel assembly construct that makes it conceptually easy and computationally efficient to move between the two abstractions. Using the information provided by the assembly construct, the compiler generates efficient in-place computation on the graph. We demonstrate that Simit is easy to use: a Simit program is typically shorter than a Matlab program; that it is high performance: a Simit program running sequentially on a CPU performs comparably to hand-optimized simulations; and that it is portable: Simit programs can be compiled for GPUs with no change to the program, delivering 4 to 20× speedups over our optimized CPU code.

While 3D movies are gaining popularity, viewers in a 3D cinema still need to wear cumbersome glasses in order to enjoy them. Automultiscopic displays provide a better alternative to the display of 3D content, as they present multiple angular images of the same scene without the need for special eyewear. However, automultiscopic displays cannot be directly implemented in a wide cinema setting due to variants of two main problems: (i) The range of angles at which the screen is observed in a large cinema is usually very wide, and there is an unavoidable tradeoff between the range of angular images supported by the display and its spatial or angular resolutions. (ii) Parallax is usually observed only when a viewer is positioned at a limited range of distances from the screen. This work proposes a new display concept, which supports automultiscopic content in a wide cinema setting. It builds on the typical structure of cinemas, such as the fixed seat positions and the fact that different rows are located on a slope at different heights. Rather than attempting to display many angular images spanning the full range of viewing angles in a wide cinema, our design only displays the narrow angular range observed within the limited width of a single seat. The same narrow range content is then replicated to all rows and seats in the cinema. To achieve this, it uses an optical construction based on two sets of parallax barriers, or lenslets, placed in front of a standard screen. This paper derives the geometry of such a display, analyzes its limitations, and demonstrates a proof-of-concept prototype.

Producing a high quality stereoscopic impression on current displays is a challenging task. The content has to be carefully prepared in order to maintain visual comfort, which typically affects the quality of depth reproduction. In this work, we show that this problem can be significantly alleviated when the eye fixation regions can be roughly estimated. We propose a new method for stereoscopic depth adjustment that utilizes eye tracking or other gaze prediction information. The key idea that distinguishes our approach from the previous work is to apply gradual depth adjustments at the eye fixation stage, so that they remain unnoticeable. To this end, we measure the limits imposed on the speed of disparity changes in various depth adjustment scenarios, and formulate a new model that can guide such seamless stereoscopic content processing. Based on this model, we propose a real-time controller that applies local manipulations to stereoscopic content to find the optimum between depth reproduction and visual comfort. We show that the controller is mostly immune to the limitations of low-cost eye tracking solutions. We also demonstrate benefits of our model in off-line applications, such as stereoscopic movie production, where skillful directors can reliably guide and predict viewers' attention or where attended image regions are identified during eye tracking sessions. We validate both our model and the controller in a series of user experiments. They show significant improvements in depth perception without sacrificing the visual quality when our techniques are applied.

Acoustic filters have a wide range of applications, yet customizing them with desired properties is difficult. Motivated by recent progress in additive manufacturing that allows for fast prototyping of complex shapes, we present a computational approach that automates the design of acoustic filters with complex geometries. In our approach, we construct an acoustic filter comprised of a set of parameterized shape primitives, whose transmission matrices can be precomputed. Using an efficient method of simulating the transmission matrix of an assembly built from these underlying primitives, our method is able to optimize both the arrangement and the parameters of the acoustic shape primitives in order to satisfy target acoustic properties of the filter. We validate our results against industrial laboratory measurements and high-quality off-line simulations. We demonstrate that our method enables a wide range of applications including muffler design, musical wind instrument prototyping, and encoding imperceptible acoustic information into everyday objects.

In this paper we propose failure probabilities as a semantically and mechanically meaningful measure of object fragility. We present a stochastic finite element method which exploits fast rigid body simulation and reduced-space approaches to compute spatially varying failure probabilities. We use an explicit rigid body simulation to emulate the real-world loading conditions an object might experience, including persistent and transient frictional contact, while allowing us to combine several such scenarios together. Thus, our estimates better reflect real-world failure modes than previous methods. We validate our results using a series of real-world tests. Finally, we show how to embed failure probabilities into a stress constrained topology optimization which we use to design objects such as weight bearing brackets and robust 3D printable objects.

We present an interactive system for computational design, optimization, and fabrication of multicopters. Our computational approach allows non-experts to design, explore, and evaluate a wide range of different multicopters. We provide users with an intuitive interface for assembling a multicopter from a collection of components (e.g., propellers, motors, and carbon fiber rods). Our algorithm interactively optimizes shape and controller parameters of the current design to ensure its proper operation. In addition, we allow incorporating a variety of other metrics (such as payload, battery usage, size, and cost) into the design process and exploring tradeoffs between them. We show the efficacy of our method and system by designing, optimizing, fabricating, and operating multicopters with complex geometries and propeller configurations. We also demonstrate the ability of our optimization algorithm to improve the multicopter performance under different metrics.

Industrial knitting machines can produce finely detailed, seamless, 3D surfaces quickly and without human intervention. However, the tools used to program them require detailed manipulation and understanding of low-level knitting operations. We present a compiler that can automatically turn assemblies of high-level shape primitives (tubes, sheets) into low-level machine instructions. These high-level shape primitives allow knit objects to be scheduled, scaled, and otherwise shaped in ways that require thousands of edits to low-level instructions. At the core of our compiler is a heuristic transfer planning algorithm for knit cycles, which we prove is both sound and complete. This algorithm enables the translation of high-level shaping and scheduling operations into needle-level operations. We show a wide range of examples produced with our compiler and demonstrate a basic visual design interface that uses our compiler as a backend.

Everyone, from a shopper buying shoes to a doctor palpating a growth, uses their sense of touch to learn about the world. 3D printing is a powerful technology because it gives us the ability to control the haptic impression an object creates. This is critical for both replicating existing, real-world constructs and designing novel ones. However, each 3D printer has different capabilities and supports different materials, leaving us to ask: How can we best replicate a given haptic result on a particular output device? In this work, we address the problem of mapping a real-world material to its nearest 3D printable counterpart by constructing a perceptual model for the compliance of nonlinearly elastic objects. We begin by building a perceptual space from experimentally obtained user comparisons of twelve 3D-printed metamaterials. By comparing this space to a number of hypothetical computational models, we identify those that can be used to accurately and efficiently evaluate human-perceived differences in nonlinear stiffness. Furthermore, we demonstrate how such models can be applied to complex geometries in an interaction-aware way where the compliance is influenced not only by the material properties from which the object is made but also its geometry. We demonstrate several applications of our method in the context of fabrication and evaluate them in a series of user experiments.

Current three-dimensional displays cannot fully reproduce all depth cues used by a human observer in the real world. Instead, they create only an illusion of looking at a three-dimensional scene. This leads to a number of challenges during the content creation process. To assure correct depth reproduction and visual comfort, either the acquisition setup has to be carefully controlled or additional postprocessing techniques have to be applied. Furthermore, these manipulations need to account for a particular setup that is used to present the content, for example, viewing distance or screen size. This creates additional challenges in the context of personal use when stereoscopic content is shown on TV sets, desktop monitors, or mobile devices. We address this problem by presenting a new system for streaming stereoscopic content. Its key feature is a computationally efficient depth adjustment technique which can automatically optimize viewing experience for videos of field sports such as soccer, football, and tennis. Additionally, the method enables depth personalization to allow users to adjust the amount of depth according to their preferences. Our stereoscopic video streaming system was implemented, deployed, and tested with real users.

A wide spread adoption of 3D videos and technologies is hindered by the lack of high-quality 3D content. One promising solution to address this problem is to use automated 2D-to-3D conversion. However, current conversion methods, while general, produce low-quality results with artifacts that are not acceptable to many viewers. We address this problem by showing how to construct a high-quality, domain-specific conversion method for soccer videos. We propose a novel, data-driven method that generates stereoscopic frames by transferring depth information from similar frames in a database of 3D stereoscopic videos. Creating a database of 3D stereoscopic videos with accurate depth is, however, very difficult. One of the key findings in this paper is showing that computer generated content in current sports computer games can be used to generate high-quality 3D video reference database for 2D-to-3D conversion methods. Once we retrieve similar 3D video frames, our technique transfers depth gradients to the target frame while respecting object boundaries. It then computes depth maps from the gradients, and generates the output stereoscopic video. We implement our method and validate it by conducting user-studies that evaluate depth perception and visual comfort of the converted 3D videos. We show that our method produces high-quality 3D videos that are almost indistinguishable from videos shot by stereo cameras. In addition, our method significantly outperforms the current state-of-the-art method. For example, up to 20% improvement in the perceived depth is achieved by our method, which translates to improving the mean opinion score from Good to Excellent.

Light field displays allow viewers to see view-dependent 3D content as if looking through a window; however, existing work on light field display interaction is limited. Yet, they have the potential to parallel 2D pen and touch screen systems, which present a joint input and display surface for natural interaction. We propose a 4D display and interaction space using a dual-purpose lenslet array, which combines light field display and light field pen sensing, and allows us to estimate the 3D position and 2D orientation of the pen. This method is simple, fast (150Hz), with position accuracy of 2-3mm and precision of 0.2-0.6mm from 0-350mm away from the lenslet array, and orientation accuracy of 2 degrees and precision of 0.2-0.3 degrees within a 45 degree field of view. Further, we 3D print the lenslet array with embedded baffles to reduce out-of-bounds cross-talk, and use an optical relay to allow interaction behind the focal plane. We demonstrate our joint display/sensing system with interactive light field painting.

Abstract We consider the problem of manufacturing free‐form geometry with classical manufacturing techniques, such as mold casting or 3‐axis milling. We determine a set of constraints that are necessary for manufacturability and then decompose and, if necessary, deform the shape to satisfy the constraints per segment. We show that many objects can be generated from a small number of (mold‐)pieces if slight deformations are acceptable. We provide examples of actual molds and the resulting manufactured objects.

Metallophones such as glockenspiels produce sounds in response to contact. Building these instruments is a complicated process, limiting their shapes to well-understood designs such as bars. We automatically optimize the shape of arbitrary 2D and 3D objects through deformation and perforation to produce sounds when struck which match user-supplied frequency and amplitude spectra. This optimization requires navigating a complex energy landscape, for which we develop Latin Complement Sampling to both speed up finding minima and provide probabilistic bounds on landscape exploration. Our method produces instruments which perform similarly to those that have been professionally-manufactured, while also expanding the scope of shape and sound that can be realized, e.g., single object chords. Furthermore, we can optimize sound spectra to create overtones and to dampen specific frequencies. Thus our technique allows even novices to design metallophones with unique sound and appearance.

We present AutoConnect, an automatic method that creates customized, 3D-printable connectors attaching two physical objects together. Users simply position and orient virtual models of the two objects that they want to connect and indicate some auxiliary information such as weight and dimensions. Then, AutoConnect creates several alternative designs that users can choose from for 3D printing. The design of the connector is created by combining two holders, one for each object. We categorize the holders into two types. The first type holds standard objects such as pipes and planes. We utilize a database of parameterized mechanical holders and optimize the holder shape based on the grip strength and material consumption. The second type holds free-form objects. These are procedurally generated shell-gripper designs created based on geometric analysis of the object. We illustrate the use of our method by demonstrating many examples of connectors and practical use cases.

Crafting the behavior of a deformable object is difficult---whether it is a biomechanically accurate character model or a new multimaterial 3D printable design. Getting it right requires constant iteration, performed either manually or driven by an automated system. Unfortunately, Previous algorithms for accelerating three-dimensional finite element analysis of elastic objects suffer from expensive precomputation stages that rely on a priori knowledge of the object's geometry and material composition. In this paper we introduce Data-Driven Finite Elements as a solution to this problem. Given a material palette, our method constructs a metamaterial library which is reusable for subsequent simulations, regardless of object geometry and/or material composition. At runtime, we perform fast coarsening of a simulation mesh using a simple table lookup to select the appropriate metamaterial model for the coarsened elements. When the object's material distribution or geometry changes, we do not need to update the metamaterial library---we simply need to update the metamaterial assignments to the coarsened elements. An important advantage of our approach is that it is applicable to non-linear material models. This is important for designing objects that undergo finite deformation (such as those produced by multimaterial 3D printing). Our method yields speed gains of up to two orders of magnitude while maintaining good accuracy. We demonstrate the effectiveness of the method on both virtual and 3D printed examples in order to show its utility as a tool for deformable object design.

We address the problem of allowing casual users to customize parametric models while maintaining their valid state as 3D-printable functional objects. We define Fab Form as any design representation that lends itself to interactive customization by a novice user, while remaining valid and manufacturable. We propose a method to achieve these Fab Form requirements for general parametric designs tagged with a general set of automated validity tests and a small number of parameters exposed to the casual user. Our solution separates Fab Form evaluation into a precomputation stage and a runtime stage. Parts of the geometry and design validity (such as manufacturability) are evaluated and stored in the precomputation stage by adaptively sampling the design space. At runtime the remainder of the evaluation is performed. This allows interactive navigation in the valid regions of the design space using an automatically generated Web user interface (UI). We evaluate our approach by converting several parametric models into corresponding Fab Forms.

We have developed a multi-material 3D printing platform that is high-resolution, low-cost, and extensible. The key part of our platform is an integrated machine vision system. This system allows for self-calibration of printheads, 3D scanning, and a closed-feedback loop to enable print corrections. The integration of machine vision with 3D printing simplifies the overall platform design and enables new applications such as 3D printing over auxiliary parts. Furthermore, our platform dramatically expands the range of parts that can be 3D printed by simultaneously supporting up to 10 different materials that can interact optically and mechanically. The platform achieves a resolution of at least 40 μm by utilizing piezoelectric inkjet printheads adapted for 3D printing. The hardware is low cost (less than $7,000) since it is built exclusively from off-the-shelf components. The architecture is extensible and modular -- adding, removing, and exchanging printing modules can be done quickly. We provide a detailed analysis of the system's performance. We also demonstrate a variety of fabricated multi-material objects.

Producing high-quality stereoscopic 3D content requires significantly more effort than preparing regular video footage. In order to assure good depth perception and visual comfort, 3D videos need to be carefully adjusted to specific viewing conditions before they are shown to viewers. While most stereoscopic 3D content is designed for viewing in movie theaters, where viewing conditions do not vary significantly, adapting the same content for viewing on home TV-sets, desktop displays, laptops, and mobile devices requires additional adjustments. To address this challenge, we propose a new system for 3D video streaming that provides automatic depth adjustments as one of its key features. Our system takes into account both the content and the display type in order to customize 3D videos and maximize their perceived quality. We propose a novel method for depth adjustment that is well-suited for videos of field sports such as soccer, football, and tennis. Our method is computationally efficient and it does not introduce any visual artifacts. We have implemented our 3D streaming system and conducted two user studies, which show: (i) adapting stereoscopic 3D videos for different displays is beneficial, and (ii) our proposed system can achieve up to 35% improvement in the perceived quality of the stereoscopic 3D content.

We present a method for transforming a 3D object into a cube or a box using a continuous folding sequence. Our method produces a single, connected object that can be physically fabricated and folded from one shape to the other. We segment the object into voxels and search for a voxel-tree that can fold from the input shape to the target shape. This involves three major steps: finding a good voxelization, finding the tree structure that can form the input and target shapes' configurations, and finding a non-intersecting folding sequence. We demonstrate our results on several input 3D objects and also physically fabricate some using a 3D printer.

Sudden temporal depth changes, such as cuts that are introduced by video edits, can significantly degrade the quality of stereoscopic content. Since usually not encountered in the real world, they are very challenging for the audience. This is because the eye vergence has to constantly adapt to new disparities in spite of conflicting accommodation requirements. Such rapid disparity changes may lead to confusion, reduced understanding of the scene, and overall attractiveness of the content. In most cases the problem cannot be solved by simply matching the depth around the transition, as this would require flattening the scene completely. To better understand this limitation of the human visual system, we conducted a series of eye-tracking experiments. The data obtained allowed us to derive and evaluate a model describing adaptation of vergence to disparity changes on a stereoscopic display. Besides computing user-specific models, we also estimated parameters of an average observer model. This enables a range of strategies for minimizing the adaptation time in the audience.

Automultiscopic screens present different images depending on the viewing direction. This enables glasses-free 3D and provides motion parallax effect. However, due to the limited angular resolution of such displays, they suffer from hot-spotting, i. e., image quality is highly affected by the viewing position. In this paper, we analyze light fields produced by lenticular and parallax-barrier displays, and show that, unlike in real world, the light fields produced by such screens have a repetitive structure. This induces visual artifacts in the form of view discontinuities, depth reversals, and excessive disparities when viewing position is not optimal. Although the problem has been always considered as inherent to the technology, we demonstrate that light fields reproduced on automultiscopic displays have enough degrees of freedom to improve the visual quality. We propose a new technique that modifies light fields using global and local shears followed by stitching to improve their continuity when displayed on a screen. We show that this enhances visual quality significantly, which is demonstrated in a series of user experiments with an automultiscopic display as well as lenticular prints.

Despite recent interest in digital fabrication, there are still few algorithms that provide control over how light propagates inside a solid object. Existing methods either work only on the surface or restrict themselves to light diffusion in volumes. We use multi-material 3D printing to fabricate objects with embedded optical fibers, exploiting total internal reflection to guide light inside an object. We introduce automatic fiber design algorithms together with new manufacturing techniques to route light between two arbitrary surfaces. Our implicit algorithm optimizes light transmission by minimizing fiber curvature and maximizing fiber separation while respecting constraints such as fiber arrival angle. We also discuss the influence of different printable materials and fiber geometry on light propagation in the volume and the light angular distribution when exiting the fiber. Our methods enable new applications such as surface displays of arbitrary shape, touch-based painting of surfaces, and sensing a hemispherical light distribution in a single shot.

We propose a data-driven method for designing 3D models that can be fabricated. First, our approach converts a collection of expert-created designs to a dataset of parameterized design templates that includes all information necessary for fabrication. The templates are then used in an interactive design system to create new fabri-cable models in a design-by-example manner. A simple interface allows novice users to choose template parts from the database, change their parameters, and combine them to create new models. Using the information in the template database, the system can automatically position, align, and connect parts: the system accomplishes this by adjusting parameters, adding appropriate constraints, and assigning connectors. This process ensures that the created models can be fabricated, saves the user from many tedious but necessary tasks, and makes it possible for non-experts to design and create actual physical objects. To demonstrate our data-driven method, we present several examples of complex functional objects that we designed and manufactured using our system.

Abstract We present a method for converting computer 3D models into physical equivalents. More specifically, we address the problem of approximating a 3D textured mesh using a small number of planar polygonal primitives that form a closed surface. This simplified representation allows us to easily manufacture individual components using computer controlled cutters (e.g., laser cutters or CNC machines). These polygonal pieces can be assembled into the final 3D model using internal planar connectors that are manufactured simultaneously. Our shape approximation algorithm iteratively assigns mesh faces to planar segments and slowly deforms these faces towards corresponding segments. This approach ensures that the output for a given closed mesh is still a closed mesh and avoids introducing self‐intersections. After this step we also compute the shape of polygonal connectors that internally hold the whole mesh surface. Both the polygonal surface elements and connectors can be manufactured in a single cutting pass. We validate the use of our method by computing and manufacturing a variety of textured polyhedral models.

Multi-material 3D printing allows objects to be composed of complex, heterogenous arrangements of materials. It is often more natural to define a functional goal than to define the material composition of an object. Translating these functional requirements to fabri-cable 3D prints is still an open research problem. Recently, several specific instances of this problem have been explored (e.g., appearance or elastic deformation), but they exist as isolated, monolithic algorithms. In this paper, we propose an abstraction mechanism that simplifies the design, development, implementation, and reuse of these algorithms. Our solution relies on two new data structures: a reducer tree that efficiently parameterizes the space of material assignments and a tuner network that describes the optimization process used to compute material arrangement. We provide an application programming interface for specifying the desired object and for defining parameters for the reducer tree and tuner network . We illustrate the utility of our framework by implementing several fabrication algorithms as well as demonstrating the manufactured results.

We present an interactive design system that allows non-expert users to create animated mechanical characters. Given an articulated character as input, the user iteratively creates an animation by sketching motion curves indicating how different parts of the character should move. For each motion curve, our framework creates an optimized mechanism that reproduces it as closely as possible. The resulting mechanisms are attached to the character and then connected to each other using gear trains, which are created in a semi-automated fashion. The mechanical assemblies generated with our system can be driven with a single input driver, such as a hand-operated crank or an electric motor, and they can be fabricated using rapid prototyping devices. We demonstrate the versatility of our approach by designing a wide range of mechanical characters, several of which we manufactured using 3D printing. While our pipeline is designed for characters driven by planar mechanisms, significant parts of it extend directly to non-planar mechanisms, allowing us to create characters with compelling 3D motions.

Multi-view autostereoscopic displays provide an immersive, glasses-free 3D viewing experience, but they require correctly filtered content from multiple viewpoints. This, however, cannot be easily obtained with current stereoscopic production pipelines. We provide a practical solution that takes a stereoscopic video as an input and converts it to multi-view and filtered video streams that can be used to drive multi-view autostereoscopic displays. The method combines a phase-based video magnification and an interperspective antialiasing into a single filtering process. The whole algorithm is simple and can be efficiently implemented on current GPUs to yield a near real-time performance. Furthermore, the ability to retarget disparity is naturally supported. Our method is robust and works well for challenging video scenes with defocus blur, motion blur, transparent materials, and specularities. We show that our results are superior when compared to the state-of-the-art depth-based rendering methods. Finally, we showcase the method in the context of a real-time 3D videoconferencing system that requires only two cameras.

Recent attempts to fabricate surfaces with custom reflectance functions boast impressive angular resolution, yet their spatial resolution is limited. In this paper we present a method to construct spatially varying reflectance at a high resolution of up to 220dpi, orders of magnitude greater than previous attempts, albeit with a lower angular resolution. The resolution of previous approaches is limited by the machining, but more fundamentally, by the geometric optics model on which they are built. Beyond a certain scale geometric optics models break down and wave effects must be taken into account. We present an analysis of incoherent reflectance based on wave optics and gain important insights into reflectance design. We further suggest and demonstrate a practical method, which takes into account the limitations of existing micro-fabrication techniques such as photolithography to design and fabricate a range of reflection effects, based on wave interference.

Force-deformation measurements of cloth exhibit significant hysteresis, and many researchers have identified internal friction as the source of this effect. However, it has not been incorporated into computer animation models of cloth. In this paper, we propose a model of internal friction based on an augmented reparameterization of Dahl's model, and we show that this model provides a good match to several important features of cloth hysteresis even with a minimal set of parameters. We also propose novel parameter estimation procedures that are based on simple and inexpensive setups and need only sparse data, as opposed to the complex hardware and dense data acquisition of previous methods. Finally, we provide an algorithm for the efficient simulation of internal friction, and we demonstrate it on simulation examples that show disparate behavior with and without internal friction.

We present a method for practical physical reproduction and design of homogeneous materials with desired subsurface scattering. Our process uses a collection of different pigments that can be suspended in a clear base material. Our goal is to determine pigment concentrations that best reproduce the appearance and subsurface scattering of a given target material. In order to achieve this task we first fabricate a collection of material samples composed of known mixtures of the available pigments with the base material. We then acquire their reflectance profiles using a custom-built measurement device. We use the same device to measure the reflectance profile of a target material. Based on the database of mappings from pigment concentrations to reflectance profiles, we use an optimization process to compute the concentration of pigments to best replicate the target material appearance. We demonstrate the practicality of our method by reproducing a variety of different translucent materials. We also present a tool that allows the user to explore the range of achievable appearances for a given set of pigments.

Lenticular prints are a popular medium for producing automultiscopic glasses-free 3D images. The light field emitted by such prints has a fixed spatial and angular resolution. We increase both perceived angular and spatial resolution by modifying the lenslet array to better match the content of a given light field. Our optimization algorithm analyzes the input light field and computes an optimal lenslet size, shape, and arrangement that best matches the input light field given a set of output parameters. The resulting emitted light field shows higher detail and smoother motion parallax compared to fixed-size lens arrays. We demonstrate our technique using rendered simulations and by 3D printing lens arrays, and we validate our approach in simulation with a user study.

3D printing hardware is rapidly scaling up to output continuous mixtures of multiple materials at increasing resolution over ever larger print volumes. This poses an enormous computational challenge: large high-resolution prints comprise trillions of voxels and petabytes of data and simply modeling and describing the input with spatially varying material mixtures at this scale is challenging. Existing 3D printing software is insufficient; in particular, most software is designed to support only a few million primitives, with discrete material choices per object. We present OpenFab, a programmable pipeline for synthesis of multi-material 3D printed objects that is inspired by RenderMan and modern GPU pipelines. The pipeline supports procedural evaluation of geometric detail and material composition, using shader-like fablets , allowing models to be specified easily and efficiently. We describe a streaming architecture for OpenFab; only a small fraction of the final volume is stored in memory and output is fed to the printer with little startup delay. We demonstrate it on a variety of multi-material objects.

We propose a method for estimating the 3D structure and the dense 3D motion (scene flow) of a dynamic nonrigid 3D scene, using a camera array. The core idea is to use a dense multi-camera array to construct a novel, dense 3D volumetric representation of the 3D space where each voxel holds an estimated intensity value and a confidence measure of this value. The problem of 3D structure and 3D motion estimation of a scene is thus reduced to a nonrigid registration of two volumes - hence the term ”Scene Registration”. Registering two dense 3D scalar volumes does not require recovering the 3D structure of the scene as a preprocessing step, nor does it require explicit reasoning about occlusions. From this nonrigid registration we accurately extract the 3D scene flow and the 3D structure of the scene, and successfully recover the sharp discontinuities in both time and space. We demonstrate the advantages of our method on a number of challenging synthetic and real data sets.

Abstract ShadowPixare white surfaces that display several prescribed images formed by the self‐shadowing of the surface when lit from certain directions. The effect is surprising and not commonly seen in the real world. We present algorithms for constructingShadowPixthat allow up to four images to be embedded in a single surface. ShadowPixcan produce a variety of unusual effects depending on the embedded images: moving the light can animate or relight the object in the image, or three colored lights may be used to produce a single colored image. ShadowPixare easy to manufacture using a 3D printer and we present photographs, videos, and renderings demonstrating these effects.

Abstract Progress in cloth simulation for computer animation and apparel design has led to a multitude of deformation models, each with its own way of relating geometry, deformation, and forces. As simulators improve, differences between these models become more important, but it is difficult to choose a model and a set of parameters to match a given real material simply by looking at simulation results. This paper provides measurement and fitting methods that allow nonlinear models to be fit to the observed deformation of a particular cloth sample. Unlike standard textile testing, our system measures complex 3D deformations of a sheet of cloth, not just one‐dimensional force‐displacement curves, so it works under a wider range of deformation conditions. The fitted models are then evaluated by comparison to measured deformations with motions very different from those used for fitting.

Abstract Our hybrid display model combines multiple automultiscopic elements volumetrically to support horizontal and vertical parallax at a larger depth of field and better accommodation cues compared to single layer elements. In this paper, we introduce a framework to analyze the bandwidth of such display devices. Based on this analysis, we show that multiple layers can achieve a wider depth of field using less bandwidth compared to single layer displays. We present a simple algorithm to distribute an input light field to multiple layers, and devise an efficient ray tracing algorithm for synthetic scenes. We demonstrate the effectiveness of our approach by both software simulation and two corresponding hardware prototypes.

We propose a complete process for designing, simulating, and fabricating synthetic skin for an animatronics character that mimics the face of a given subject and its expressions. The process starts with measuring the elastic properties of a material used to manufacture synthetic soft tissue. Given these measurements we use physics-based simulation to predict the behavior of a face when it is driven by the underlying robotic actuation. Next, we capture 3D facial expressions for a given target subject. As the key component of our process, we present a novel optimization scheme that determines the shape of the synthetic skin as well as the actuation parameters that provide the best match to the target expressions. We demonstrate this computational skin design by physically cloning a real human face onto an animatronics figure.

Binocular disparity is one of the most important depth cues used by the human visual system. Recently developed stereo-perception models allow us to successfully manipulate disparity in order to improve viewing comfort, depth discrimination as well as stereo content compression and display. Nonetheless, all existing models neglect the substantial influence of luminance on stereo perception. Our work is the first to account for the interplay of luminance contrast (magnitude/frequency) and disparity and our model predicts the human response to complex stereo-luminance images. Besides improving existing disparity-model applications (e.g., difference metrics or compression), our approach offers new possibilities, such as joint luminance contrast and disparity manipulation or the optimization of auto-stereoscopic content. We validate our results in a user study, which also reveals the advantage of considering luminance contrast and its significant impact on disparity manipulation techniques.

3D printing technology is rapidly maturing and becoming ubiquitous. One of the remaining obstacles to wide-scale adoption is that the object to be printed must fit into the working volume of the 3D printer. We propose a framework, called Chopper, to decompose a large 3D object into smaller parts so that each part fits into the printing volume. These parts can then be assembled to form the original object. We formulate a number of desirable criteria for the partition, including assemblability, having few components, unobtrusiveness of the seams, and structural soundness. Chopper optimizes these criteria and generates a partition either automatically or with user guidance. Our prototype outputs the final decomposed parts with customized connectors on the interfaces. We demonstrate the effectiveness of Chopper on a variety of non-trivial real-world objects.

This paper introduces the video mesh, a data structure for representing video as 2.5D “paper cutouts.” The video mesh allows interactive editing of moving objects and modeling of depth, which enables 3D effects and post-exposure camera control. The video mesh sparsely encodes optical flow as well as depth, and handles occlusion using local layering and alpha mattes. Motion is described by a sparse set of points tracked over time. Each point also stores a depth value. The video mesh is a triangulation over this point set and per-pixel information is obtained by interpolation. The user rotoscopes occluding contours and we introduce an algorithm to cut the video mesh along them. Object boundaries are refined with per-pixel alpha values. The video mesh is at its core a set of texture mapped triangles, we leverage graphics hardware to enable interactive editing and rendering of a variety of effects. We demonstrate the effectiveness of our representation with special effects such as 3D viewpoint changes, object insertion, depth-of-field manipulation, and 2D to 3D video conversion.

Abstract We propose a novel system for designing and manufacturing surfaces that produce desired caustic images when illuminated by a light source. Our system is based on a nonnegative image decomposition using a set of possibly overlapping anisotropic Gaussian kernels. We utilize this decomposition to construct an array of continuous surface patches, each of which focuses light onto one of the Gaussian kernels, either through refraction or reflection. We show how to derive the shape of each continuous patch and arrange them by performing a discrete assignment of patches to kernels in the desired caustic. Our decomposition provides for high fidelity reconstruction of natural images using a small collection of patches. We demonstrate our approach on a wide variety of caustic images by manufacturing physical surfaces with a small number of patches.

We present a method for replacing facial performances in video. Our approach accounts for differences in identity, visual appearance, speech, and timing between source and target videos. Unlike prior work, it does not require substantial manual operation or complex acquisition hardware, only single-camera video. We use a 3D multilinear model to track the facial performance in both videos. Using the corresponding 3D geometry, we warp the source to the target face and retime the source to match the target performance. We then compute an optimal seam through the video volume that maintains temporal consistency in the final composite. We showcase the use of our method on a variety of examples and present the result of a user study that suggests our results are difficult to distinguish from real video footage.

Stereoscopic 3D has gained significant importance in the entertainment industry. However, production of high quality stereoscopic content is still a challenging art that requires mastering the complex interplay of human perception, 3D display properties, and artistic intent. In this paper, we present a computational stereo camera system that closes the control loop from capture and analysis to automatic adjustment of physical parameters. Intuitive interaction metaphors are developed that replace cumbersome handling of rig parameters using a touch screen interface with 3D visualization. Our system is designed to make stereoscopic 3D production as easy, intuitive, flexible, and reliable as possible. Captured signals are processed and analyzed in real-time on a stream processor. Stereoscopy and user settings define programmable control functionalities, which are executed in real-time on a control processor. Computational power and flexibility is enabled by a dedicated software and hardware architecture. We show that even traditionally difficult shots can be easily captured using our system.

We present a method for automatically converting a digital 3D model into a multilayer model : a parallel stack of high-resolution 2D images embedded within a semi-transparent medium. Multilayer models can be produced quickly and cheaply and provide a strong sense of an object's 3D shape and texture over a wide range of viewing directions. Our method is designed to minimize visible cracks and other artifacts that can arise when projecting an input model onto a small number of parallel planes, and avoid layer transitions that cut the model along important surface features. We demonstrate multilayer models fabricated with glass and acrylic tiles using commercially available printers.

This paper addresses stereoscopic view generation from a light field. We present a framework that allows for the generation of stereoscopic image pairs with per-pixel control over disparity, based on multi-perspective imaging from light fields. The proposed framework is novel and useful for stereoscopic image processing and post-production. The stereoscopic images are computed as piecewise continuous cuts through a light field, minimizing an energy reflecting prescribed parameters such as depth budget, maximum disparity gradient, desired stereoscopic baseline, and so on. As demonstrated in our results, this technique can be used for efficient and flexible stereoscopic post-processing, such as reducing excessive disparity while preserving perceived depth, or retargeting of already captured scenes to various view settings. Moreover, we generalize our method to multiple cuts, which is highly useful for content creation in the context of multi-view autostereoscopic displays. We present several results on computer-generated content as well as live-action content.

Computer-generated (CG) images have achieved high levels of realism. This realism, however, comes at the cost of long and expensive manual modeling, and often humans can still distinguish between CG and real images. We introduce a new data-driven approach for rendering realistic imagery that uses a large collection of photographs gathered from online repositories. Given a CG image, we retrieve a small number of real images with similar global structure. We identify corresponding regions between the CG and real images using a mean-shift cosegmentation algorithm. The user can then automatically transfer color, tone, and texture from matching regions to the CG image. Our system only uses image processing operations and does not require a 3D model of the scene, making it fast and easy to integrate into digital content creation workflows. Results of a user study show that our hybrid images appear more realistic than the originals.

Although there has been much interest in computational photography within the research and photography communities, progress has been hampered by the lack of a portable, programmable camera with sufficient image quality and computing power. To address this problem, we have designed and implemented an open architecture and API for such cameras: the Frankencamera. It consists of a base hardware specification, a software stack based on Linux, and an API for C++. Our architecture permits control and synchronization of the sensor and image processing pipeline at the microsecond time scale, as well as the ability to incorporate and synchronize external hardware like lenses and flashes. This paper specifies our architecture and API, and it describes two reference implementations we have built. Using these implementations we demonstrate six computational photography applications: HDR viewfinding and capture, low-light viewfinding and capture, automated acquisition of extended dynamic range panoramas, foveal imaging, IMU-based hand shake detection, and rephotography. Our goal is to standardize the architecture and distribute Frankencameras to researchers and students, as a step towards creating a community of photographer-programmers who develop algorithms, applications, and hardware for computational cameras.

We describe how to create relief surfaces whose diffuse reflection approximates given images under known directional illumination. This allows using any surface with a significant diffuse reflection component as an image display. We propose a discrete model for the area in the relief surface that corresponds to a pixel in the desired image. This model introduces the necessary degrees of freedom to overcome theoretical limitations in shape from shading and practical requirements such as stability of the image under changes in viewing condition and limited overall variation in depth. The discrete surface is determined using an iterative least squares optimization. We show several resulting relief surfaces conveying one image for varying lighting directions as well as two images for two specific lighting directions.

This paper introduces a data-driven process for designing and fabricating materials with desired deformation behavior. Our process starts with measuring deformation properties of base materials. For each base material we acquire a set of example deformations, and we represent the material as a non-linear stress-strain relationship in a finite-element model. We have validated our material measurement process by comparing simulations of arbitrary stacks of base materials with measured deformations of fabricated material stacks. After material measurement, our process continues with designing stacked layers of base materials. We introduce an optimization process that finds the best combination of stacked layers that meets a user's criteria specified by example deformations. Our algorithm employs a number of strategies to prune poor solutions from the combinatorial search space. We demonstrate the complete process by designing and fabricating objects with complex heterogeneous materials using modern multi-material 3D printers.

We investigate a complete pipeline for measuring, modeling, and fabricating objects with specified subsurface scattering behaviors. The process starts with measuring the scattering properties of a given set of base materials, determining their radial reflection and transmission profiles. We describe a mathematical model that predicts the profiles of different stackings of base materials, at arbitrary thicknesses. In an inverse process, we can then specify a desired reflection profile and compute a layered composite material that best approximates it. Our algorithm efficiently searches the space of possible combinations of base materials, pruning unsatisfactory states imposed by physical constraints. We validate our process by producing both homogeneous and heterogeneous composites fabricated using a multi-material 3D printer. We demonstrate reproductions that have scattering properties approximating complex materials.

We describe a framework for improving the quality of personal photos by using a person's favorite photographs as examples. We observe that the majority of a person's photographs include the faces of a photographer's family and friends and often the errors in these photographs are the most disconcerting. We focus on correcting these types of images and use common faces across images to automatically perform both global and face-specific corrections. Our system achieves this by using face detection to align faces between “good” and “bad” photos such that properties of the good examples can be used to correct a bad photo. These “personal” photos provide strong guidance for a number of operations and, as a result, enable a number of high-quality image processing operations. We illustrate the power and generality of our approach by presenting a novel deblurring algorithm, and we show corrections that perform sharpening, superresolution, in-painting of over- and underexposured regions, and white-balancing.

Computational highlight holography converts three-dimensional computer models into mechanical "holograms" fabricated on (specular) reflective or refractive materials. The surface consists of small grooves with patches of paraboloids or hyperboloids, each of which produces a highlight when illuminated by a directional light. Each highlight appears in different places for different view directions, with the correct binocular and motion parallax corresponding to a virtual 3D point position. Our computational pipeline begins with a 3D model and desired view position, samples the model to generate points that depict its features accurately, and computes a maximal set of non-overlapping patches to be embedded in the surface. We provide a preview of the hologram for the user, then fabricate the surface using a computer-controlled engraving machine. We show a variety of different fabricated holograms: reflective, transmissive, and holograms with color and proper shading. We also present extensions to stationary and animated 2D stippled images.

Traditional image compositing techniques, such as alpha matting and gradient domain compositing, are used to create composites that have plausible boundaries. But when applied to images taken from different sources or shot under different conditions, these techniques can produce unrealistic results. In this work, we present a framework that explicitly matches the visual appearance of images through a process we call image harmonization , before blending them. At the heart of this framework is a multi-scale technique that allows us to transfer the appearance of one image to another. We show that by carefully manipulating the scales of a pyramid decomposition of an image, we can match contrast, texture, noise, and blur, while avoiding image artifacts. The output composite can then be reconstructed from the modified pyramid coefficients while enforcing both alpha-based and seamless boundary constraints. We show how the proposed framework can be used to produce realistic composites with minimal user interaction in a number of different scenarios.

We present an image restoration method that leverages a large database of images gathered from the web. Given an input image, we execute an efficient visual search to find the closest images in the database; these images define the input's visual context. We use the visual context as an image-specific prior and show its value in a variety of image restoration operations, including white balance correction, exposure correction, and contrast enhancement. We evaluate our approach using a database of 1 million images downloaded from Flickr and demonstrate the effect of database size on performance. Our results show that priors based on the visual context consistently out-perform generic or even domain-specific priors for these operations.

This paper introduces a data-driven representation and modeling technique for simulating non-linear heterogeneous soft tissue. It simplifies the construction of convincing deformable models by avoiding complex selection and tuning of physical material parameters, yet retaining the richness of non-linear heterogeneous behavior. We acquire a set of example deformations of a real object, and represent each of them as a spatially varying stress-strain relationship in a finite-element model. We then model the material by non-linear interpolation of these stress-strain relationships in strain-space. Our method relies on a simple-to-build capture system and an efficient run-time simulation algorithm based on incremental loading, making it suitable for interactive computer graphics applications. We present the results of our approach for several non-linear materials and biological soft tissue, with accurate agreement of our model to the measured data.

We describe a method for plausible interpolation of images, with a wide range of applications like temporal up-sampling for smooth playback of lower frame rate video, smooth view interpolation, and animation of still images. The method is based on the intuitive idea, that a given pixel in the interpolated frames traces out a path in the source images. Therefore, we simply move and copy pixel gradients from the input images along this path. A key innovation is to allow arbitrary (asymmetric) transition points , where the path moves from one image to the other. This flexible transition preserves the frequency content of the originals without ghosting or blurring, and maintains temporal coherence. Perhaps most importantly, our framework makes occlusion handling particularly simple. The transition points allow for matches away from the occluded regions, at any suitable point along the path. Indeed, occlusions do not need to be handled explicitly at all in our initial graph-cut optimization. Moreover, a simple comparison of computed path lengths after the optimization, allows us to robustly identify occluded regions, and compute the most plausible interpolation in those areas. Finally, we show that significant improvements are obtained by moving gradients and using Poisson reconstruction.

Although real-world surfaces can exhibit significant variation in materials --- glossy, diffuse, metallic, etc. --- printers are usually used to reproduce color or gray-scale images. We propose a complete system that uses appropriate inks and foils to print documents with a variety of material properties. Given a set of inks with known Bidirectional Reflectance Distribution Functions (BRDFs), our system automatically finds the optimal linear combinations to approximate the BRDFs of the target documents. Novel gamut-mapping algorithms preserve the relative glossiness between different BRDFs, and halftoning is used to produce patterns to be sent to the printer. We demonstrate the effectiveness of this approach with printed samples of a number of measured spatially-varying BRDFs.

In this article we propose a new framework for capturing light transport data of a real scene, based on the recently developed theory of compressive sensing. Compressive sensing offers a solid mathematical framework to infer a sparse signal from a limited number of nonadaptive measurements. Besides introducing compressive sensing for fast acquisition of light transport to computer graphics, we develop several innovations that address specific challenges for image-based relighting, and which may have broader implications. We develop a novel hierarchical decoding algorithm that improves reconstruction quality by exploiting interpixel coherency relations. Additionally, we design new nonadaptive illumination patterns that minimize measurement noise and further improve reconstruction quality. We illustrate our framework by capturing detailed high-resolution reflectance fields for image-based relighting.

We describe a system for high-resolution capture of moving 3D geometry, beginning with dynamic normal maps from multiple views. The normal maps are captured using active shape-from-shading (photometric stereo), with a large lighting dome providing a series of novel spherical lighting configurations. To compensate for low-frequency deformation, we perform multi-view matching and thin-plate spline deformation on the initial surfaces obtained by integrating the normal maps. Next, the corrected meshes are merged into a single mesh using a volumetric method. The final output is a set of meshes, which were impossible to produce with previous methods. The meshes exhibit details on the order of a few millimeters, and represent the performance over human-size working volumes at a temporal resolution of 60Hz.

We propose a system for manufacturing physical surfaces that, in aggregate, exhibit a desired surface appearance. Our system begins with a user specification of a BRDF, or simply a highlight shape, and infers the required distribution of surface slopes. We sample this distribution, optimize for a maximally-continuous and valley-minimizing height field, and finally mill the surface using a computer-controlled machine tool. We demonstrate a variety of surfaces, ranging from reproductions of measured BRDFs to materials with unconventional highlights.

Automultiscopic displays show 3D stereoscopic images that can be viewed from any viewpoint without special glasses. These displays are becoming widely available and affordable. In this paper, we describe how an automultiscopic display, built for viewing 3D images, can be repurposed to display 2D interfaces that appear differently from different points-of-view. For single-user applications, point-of-view becomes a means of input and a user is able to reveal different views of an application by simply moving their head left and right. For multi-user applications, a single-display application can show each member of the group a different variation of the interface. We outline three types of multi-view interfaces and illustrate each with example applications.

In an extended image sequence of an outdoor scene, one observes changes in color induced by variations in the spectral composition of daylight. This paper proposes a model for these temporal color changes and explores its use for the analysis of outdoor scenes from time-lapse video data. We show that the time-varying changes in direct sunlight and ambient skylight can be recovered with this model, and that an image sequence can be decomposed into two corresponding components. The decomposition provides access to both radiometric and geometric information about a scene, and we demonstrate how this can be exploited for a variety of visual tasks, including color-constancy, background subtraction, shadow detection, scene reconstruction, and camera geo-location.

We accurately capture the shape and appearance of a person's hairstyle. We use triangulation and a sweep with planes of light for the geometry. Multiple projectors and cameras address the challenges raised by the reflectance and intricate geometry of hair. We introduce the use of structure tensors to infer the hidden geometry between the hair surface and the scalp. Our triangulation approach affords substantial accuracy improvement and we are able to measure elaborate hair geometry including complex curls and concavities. To reproduce the hair appearance, we capture a six-dimensional reflectance field. We introduce a new reflectance interpolation technique that leverages an analytical reflectance model to alleviate cross-fading artifacts caused by linear methods. Our results closely match the real hairstyles and can be used for animation.

Details in mesh animations are difficult to generate but they have great impact on visual quality. In this work, we demonstrate a practical software system for capturing such details from multi-view video recordings. Given a stream of synchronized video images that record a human performance from multiple viewpoints and an articulated template of the performer, our system captures the motion of both the skeleton and the shape. The output mesh animation is enhanced with the details observed in the image silhouettes. For example, a performance in casual loose-fitting clothes will generate mesh animations with flowing garment motions. We accomplish this with a fast pose tracking method followed by nonrigid deformation of the template to fit the silhouettes. The entire process takes less than sixteen seconds per frame and requires no markers or texture cues. Captured meshes are in full correspondence making them readily usable for editing operations including texturing, deformation transfer, and deformation model learning.

The proliferation of low-cost infrared cameras gives us a new angle for attacking many unsolved vision problems by leveraging a larger range of the electromagnetic spectrum. A first step to utilizing these images is to explore the statistics of infrared images and compare them to the corresponding statistics in the visible spectrum. In this paper, we analyze the power spectra as well as the marginal and joint wavelet coefficient distributions of datasets of indoor and outdoor images. We note that infrared images have noticeably less texture indoors where temperatures are more homogenous. The joint wavelet statistics also show strong correlation between object boundaries in IR and visible images, leading to high potential for vision applications using a combined statistical model.

Occlusion is a significant challenge for many tracking algorithms. Most current methods can track through transient occlusion, but cannot handle significant extended occlusion when the object's trajectory may change significantly. We present a method to track a 3D object through significant occlusion using multiple nearby cameras (e.g., a camera array). When an occluder and object are at different depths, different parts of the object are visible or occluded in each view due to parallax. By aggregating across these views, the method can track even when any individual camera observes very little of the target object. Implementation- wise, the methods are straightforward and build upon established single-camera algorithms. They do not require explicit modeling or reconstruction of the scene and enable tracking in complex, dynamic scenes with moving cameras. Analysis of accuracy and robustness shows that these methods are successful when upwards of '70% of the object is occluded in every camera view. To the best of our knowledge, this system is the first capable of tracking in the presence of such significant occlusion.

This paper addresses signal processing issues related to coded representation, reconstruction and rendering of multiview video for 3D displays. We provide an overview of standardization efforts for multiview video that are aimed at reducing data rates required to represent the multiview video in compressed form. We then present an anti-aliasing filtering technique that effectively eliminates ghosting artifacts when rendering multiview video on 3D displays. Since high-frequency components of the signal are removed, substantial reductions in the compressed data rate could also be realized. Finally, we discuss the importance of scalability in the context of multiview video coding and suggest a combined anti-aliasing and scalable decoding scheme to minimize decoding resources for a given 3D display.

Multi-view 3D displays are preferable to other stereoscopic display technologies because they provide autostereoscopic viewing from any viewpoint without special glasses. However, they require a large number of pixels to achieve high image quality. Therefore, data compression is a major issue for this approach. In this paper, we present a framework for efficient compression of multi-view video streams for multi-view 3D displays. Our goal is to optimize image quality without increasing the required data bandwidth. We achieve this by taking into account a precise notion of the multi-dimensional display bandwidth. The display bandwidth implies that scene elements that appear at a given distance from the display become increasingly blurry as the distance grows. Our main contribution is to enhance conventional multi-view compression pipelines with an additional pre-filtering step that bandlimits the multi-view signal to the display bandwidth. This imposes a shallow depth of field on the input images, thereby removing high frequency content. We show that this pre-filtering step leads to increased image quality compared to state-of-the-art multi-view coding at equal bitrate. We present results of an extensive user study that corroborate the benefits of our approach. Our work suggests that display pre-filtering will be a fundamental component in signal processing for 3D displays, and that any multi-view compression scheme will benefit from our pre-filtering technique.

We present a novel multi-scale representation and acquisition method for the animation of high-resolution facial geometry and wrinkles. We first acquire a static scan of the face including reflectance data at the highest possible quality. We then augment a traditional marker-based facial motion-capture system by two synchronized video cameras to track expression wrinkles. The resulting model consists of high-resolution geometry, motion-capture data, and expression wrinkles in 2D parametric form. This combination represents the facial shape and its salient features at multiple scales. During motion synthesis the motion-capture data deforms the high-resolution geometry using a linear shell-based mesh-deformation method. The wrinkle geometry is added to the facial base mesh using nonlinear energy optimization. We present the results of our approach for performance replay as well as for wrinkle editing.

The emergent field of computational photography is proving that, by coupling generalized imaging optics with software processing, the quality and flexibility of imaging systems can be increased. In this paper, we capture and manipulate multiple images of a scene taken with different aperture settings ( f -numbers). We design and implement a prototype optical system and associated algorithms to capture four images of the scene in a single exposure, each taken with a different aperture setting. Our system can be used with commercially available DSLR cameras and photographic lenses without modification to either. We leverage the fact that defocus blur is a function of scene depth and f /# to estimate a depth map. We demonstrate several applications of our multi-aperture camera, such as post-exposure editing of the depth of field, including extrapolation beyond the physical limits of the lens, synthetic refocusing, and depth-guided deconvolution.

We propose a novel post-production facial performance relighting system for human actors. Our system uses just a dataset of view-dependent facial appearances with a neutral expression, captured for a static subject using a Light Stage apparatus. For the actual performance, however, a potentially different actor is captured under known, but static, illumination. During post-production, the reflectance field of the reference dataset actor is transferred onto the dynamic performance, enabling image-based relighting of the entire sequence. Our approach makes post-production relighting more practical and could easily be incorporated in a traditional production pipeline since it does not require additional hardware during principal photography. Additionally, we show that our system is suitable for real-time post-production illumination editing.

We describe a method for converting time-lapse photography captured with outdoor cameras into Factored Time-Lapse Video (FTLV): a video in which time appears to move faster (i.e., lapsing) and where data at each pixel has been factored into shadow, illumination, and reflectance components. The factorization allows a user to easily relight the scene, recover a portion of the scene geometry (normals), and to perform advanced image editing operations. Our method is easy to implement, robust, and provides a compact representation with good reconstruction characteristics. We show results using several publicly available time-lapse sequences.

Commercial motion-capture systems produce excellent in-studio reconstructions, but offer no comparable solution for acquisition in everyday environments. We present a system for acquiring motions almost anywhere. This wearable system gathers ultrasonic time-of-flight and inertial measurements with a set of inexpensive miniature sensors worn on the garment. After recording, the information is combined using an Extended Kalman Filter to reconstruct joint configurations of a body. Experimental results show that even motions that are traditionally difficult to acquire are recorded with ease within their natural settings. Although our prototype does not reliably recover the global transformation, we show that the resulting motions are visually similar to the original ones, and that the combined acoustic and intertial system reduces the drift commonly observed in purely inertial systems. Our final results suggest that this system could become a versatile input device for a variety of augmented-reality applications.

We propose a real-time method for rendering rigid objects with complex view-dependent effects under distant all-frequency lighting. Existing precomputed light transport approaches can render rich global illumination effects, but high-frequency view-dependent effects such as sharp highlights remain a challenge. We introduce a new representation of the light transport operator based on sums of Gaussians. The nonlinear parameters of our representation enable 1) arbitrary bandwidth because scale is encoded as a direct parameter, and 2) high-quality interpolation across view and mesh triangles because we interpolate the mean direction of the Gaussians, thereby preventing linear cross-fading artifacts. However, fitting the precomputed light transport data to this new representation requires solving a nonlinear regression problem that is more involved than traditional linear and nonlinear (truncation) approximation techniques. We present a new data fitting method based on optimization that includes energy terms aimed at enforcing artifact-free interpolation. We demonstrate that our method achieves high visual quality with a small storage cost and an efficient rendering algorithm.

Detailed surface geometry contributes greatly to the visual realism of 3D face models. However, acquiring high-resolution face geometry is often tedious and expensive. Consequently, most face models used in games, virtual reality, or computer vision look unrealistically smooth. In this paper, we introduce a new statistical technique for the analysis and synthesis of small three-dimensional facial features, such as wrinkles and pores. We acquire high-resolution face geometry for people across a wide range of ages, genders, and races. For each scan, we separate the skin surface details from a smooth base mesh using displaced subdivision surfaces. Then, we analyze the resulting displacement maps using the texture analysis/synthesis framework of Heeger and Bergen, adapted to capture statistics that vary spatially across a face. Finally, we use the extracted statistics to synthesize plausible detail on face meshes of arbitrary subjects. We demonstrate the effectiveness of this method in several applications, including analysis of facial texture in subjects with different ages and genders, interpolation between high-resolution face scans, adding detail to low-resolution face scans, and adjusting the apparent age of faces. In all cases, we are able to re-produce fine geometric details consistent with those observed in high resolution scans.

For computer graphics rendering, we generally assume that the appearance of surfaces remains static over time. Yet, there are a number of natural processes that cause surface appearance to vary dramatically, such as burning of wood, wetting and drying of rock and fabric, decay of fruit skins, and corrosion and rusting of steel and copper. In this paper, we take a significant step towards measuring, modeling, and rendering time-varying surface appearance. We describe the acquisition of the first time-varying database of 26 samples, encompassing a variety of natural processes including burning, drying, decay, and corrosion. Our main technical contribution is a Space-Time Appearance Factorization (STAF). This model factors space and time-varying effects. We derive an overall temporal appearance variation characteristic curve of the specific process, as well as space-dependent textures, rates, and offsets. This overall temporal curve controls different spatial locations evolve at the different rates, causing spatial patterns on the surface over time. We show that the model accurately represents a variety of phenomena. Moreover, it enables a number of novel rendering applications, such as transfer of the time-varying effect to a new static surface, control to accelerate time evolution in certain areas, extrapolation beyond the acquired sequence, and texture synthesis of time-varying appearance.

We present an algorithm and a system for high-quality natural video matting using a camera array. The system uses high frequencies present in natural scenes to compute mattes by creating a synthetic aperture image that is focused on the foreground object, which reduces the variance of pixels reprojected from the foreground while increasing the variance of pixels reprojected from the background. We modify the standard matting equation to work directly with variance measurements and show how these statistics can be used to construct a trimap that is later upgraded to an alpha matte. The entire process is completely automatic, including an automatic method for focusing the synthetic aperture image on the foreground object and an automatic method to compute the trimap and the alpha matte. The proposed algorithm is very efficient and has a per-pixel running time that is linear in the number of cameras. Our current system runs at several frames per second, and we believe that it is the first system capable of computing high-quality alpha mattes at near real-time rates without the use of active illumination or special backgrounds.

Recent progress in the measurement of surface reflectance has created a demand for non-parametric appearance representations that are accurate, compact, and easy to use for rendering. Another crucial goal, which has so far received little attention, is editability: for practical use, we must be able to change both the directional and spatial behavior of surface reflectance (e.g., making one material shinier, another more anisotropic, and changing the spatial "texture maps" indicating where each material appears). We introduce an Inverse Shade Tree framework that provides a general approach to estimating the "leaves" of a user-specified shade tree from high-dimensional measured datasets of appearance. These leaves are sampled 1- and 2-dimensional functions that capture both the directional behavior of individual materials and their spatial mixing patterns. In order to compute these shade trees automatically, we map the problem to matrix factorization and introduce a flexible new algorithm that allows for constraints such as non-negativity, sparsity, and energy conservation. Although we cannot infer every type of shade tree, we demonstrate the ability to reduce multi-gigabyte measured datasets of the Spatially-Varying Bidirectional Reflectance Distribution Function (SVBRDF) into a compact representation that may be edited in real time.

Many translucent materials exhibit heterogeneous subsurface scattering, which arises from complex internal structures. The acquisition and representation of these scattering functions is a complex problem that has been only partially addressed in previous techniques. Unlike homogeneous materials, the spatial component of heterogeneous subsurface scattering can vary arbitrarily over surface locations. Storing the spatial component without compression leads to impractically large datasets. In this paper, we address the problem of acquiring and compactly representing the spatial component of heterogeneous subsurface scattering functions. We propose a material model based on matrix factorization that can be mapped onto arbitrary geometry, and, due to its compact form, can be incorporated into most visualization systems with little overhead. We present results of several real-world datasets that are acquired using a projector and a digital camera.

We have measured 3D face geometry, skin reflectance, and subsurface scattering using custom-built devices for 149 subjects of varying age, gender, and race. We developed a novel skin reflectance model whose parameters can be estimated from measurements. The model decomposes the large amount of measured skin data into a spatially-varying analytic BRDF, a diffuse albedo map, and diffuse subsurface scattering. Our model is intuitive, physically plausible, and -- since we do not use the original measured data -- easy to edit as well. High-quality renderings come close to reproducing real photographs. The analysis of the model parameters for our sample population reveals variations according to subject age, gender, skin type, and external factors (e.g., sweat, cold, or makeup). Using our statistics, a user can edit the overall appearance of a face (e.g., changing skin type and age) or change small-scale features using texture synthesis (e.g., adding moles and freckles). We are making the collected statistics publicly available to the research community for applications in face synthesis and analysis.

We present a system for designing novel textures in the space of textures induced by an input database. We capture the structure of the induced space by a simplicial complex where vertices of the simplices represent input textures. A user can generate new textures by interpolating within individual simplices. We propose a morphable interpolation for textures, which also defines a metric used to build the simplicial complex. To guarantee sharpness in interpolated textures, we enforce histograms of high-frequency content using a novel method for histogram interpolation. We allow users to continuously navigate in the simplicial complex and design new textures using a simple and efficient user interface. We demonstrate the usefulness of our system by integrating it with a 3D texture painting application, where the user interactively designs desired textures.

Video matting is the process of pulling a high-quality alpha matte and foreground from a video sequence. Current techniques require either a known background (e.g., a blue screen) or extensive user interaction (e.g., to specify known foreground and background elements). The matting problem is generally under-constrained, since not enough information has been collected at capture time. We propose a novel, fully autonomous method for pulling a matte using multiple synchronized video streams that share a point of view but differ in their plane of focus. The solution is obtained by directly minimizing the error in filter-based image formation equations, which are over-constrained by our rich data stream. Our system solves the fully dynamic video matting problem without user assistance: both the foreground and background may be high frequency and have dynamic content, the foreground may resemble the background, and the scene is lit by natural (as opposed to polarized or collimated) illumination.

Three-dimensional TV is expected to be the next revolution in the history of television. We implemented a 3D TV prototype system with real-time acquisition, transmission, and 3D display of dynamic scenes. We developed a distributed, scalable architecture to manage the high computation and bandwidth demands. Our system consists of an array of cameras, clusters of network-connected PCs, and a multi-projector 3D display. Multiple video streams are individually encoded and sent over a broadband network to the display. The 3D display shows high-resolution (1024 × 768) stereoscopic color images for multiple viewpoints without special glasses. We implemented systems with rear-projection and front-projection lenticular screens. In this paper, we provide a detailed overview of our 3D TV system, including an examination of design choices and tradeoffs. We present the calibration and image alignment procedures that are necessary to achieve good image quality. We present qualitative results and some early user feedback. We believe this is the first real-time end-to-end 3D TV system with enough views and resolution to provide a truly immersive 3D experience.

We present new hardware-accelerated techniques for rendering surface light fields with opacity hulls that allow for interactive visualization of objects that have complex reflectance properties and elaborate geometrical details. The opacity hull is a shape enclosing the object with view-dependent opacity parameterized onto that shape. We call the combination of opacity hulls and surface light fields the opacity light field. Opacity light fields are ideally suited for rendering of the visually complex objects and scenes obtained with 3D photography. We show how to implement opacity light fields in the framework of three surface light field rendering methods: view-dependent texture mapping, unstructured lumigraph rendering, and light field mapping. The modified algorithms can be effectively supported on modern graphics hardware. Our results show that all three implementations are able to achieve interactive or real-time frame rates.

We present a generative model for isotropic bidirectional reflectance distribution functions (BRDFs) based on acquired reflectance data. Instead of using analytical reflectance models, we represent each BRDF as a dense set of measurements. This allows us to interpolate and extrapolate in the space of acquired BRDFs to create new BRDFs. We treat each acquired BRDF as a single high-dimensional vector taken from a space of all possible BRDFs. We apply both linear (subspace) and non-linear (manifold) dimensionality reduction tools in an effort to discover a lower-dimensional representation that characterizes our measurements. We let users define perceptually meaningful parametrization directions to navigate in the reduced-dimension BRDF space. On the low-dimensional manifold, movement along these directions produces novel but valid BRDFs.

We have built a system for acquiring and displaying high quality graphical models of objects that are impossible to scan with traditional scanners. Our system can acquire highly specular and fuzzy materials, such as fur and feathers. The hardware set-up consists of a turntable, two plasma displays, an array of cameras, and a rotating array of directional lights. We use multi-background matting techniques to acquire alpha mattes of the object from multiple viewpoints. The alpha mattes are used to construct an opacity hull. The opacity hull is a new shape representation, defined as the visual hull of the object with view-dependent opacity. It enables visualization of complex object silhouettes and seamless blending of objects into new environments. Our system also supports relighting of objects with arbitrary appearance using surface reflectance fields, a purely image-based appearance representation. Our system is the first to acquire and render surface reflectance fields under varying illumination from arbitrary viewpoints. We have built three generations of digitizers with increasing sophistication. In this paper, we present our results from digitizing hundreds of models.

In this paper, we describe an efficient image-based approach to computing and shading visual hulls from silhouette image data. Our algorithm takes advantage of epipolar geometry and incremental computation to achieve a constant rendering cost per rendered pixel. It does not suffer from the computation complexity, limited resolution, or quantization artifacts of previous volumetric approaches. We demonstrate the use of this algorithm in a real-time virtualized reality application running off a small number of video streams. Keywords: Computer Vision, Image-Based Rendering, Constructive Solid Geometry, Misc. Rendering Algorithms. 1 Introduction Visualizing and navigating within virtual environments composed of both real and synthetic objects has been a long-standing goal of computer graphics. The term "Virtualized Reality^TM", as popularized by Kanade [23], describes a setting where a real-world scene is "captured" by a collection of cameras and then viewed through a virtual camera, a...