Section 1 introduces the details of our capture procedure for capturing new sequences for DyTact-21 benchmark. Section 2 discusses how we visualize the contact map. Section 3 describes the implementation details of DyTact. Section 4 shows more qualitative comparisons on novel view synthesis. Section 5 provides a detailed related work. Section 6 discusses limitations and future work. We kindly refer readers to our supplementary video for more results.

Large-scale pre-trained video diffusion models have exhibited remarkable capabilities in diverse video generation. However, existing solutions face several challenges in generating long videos with rich human–scene interactions (HSI), including unrealistic dynamics and affordance, lack of subject identity preservation, and the need for expensive training. To this end, we propose GenHSI, a training-free method for controllable generation of long HSI videos with 3D awareness. Taking inspiration from movie animation, we subdivide the video synthesis into three stages: (1) script writing, (2) pre-visualization, and (3) animation. Given an image of a scene and a character with a user description, we use these three stages to generate long videos that preserve human identity and provide rich and plausible HSI. Script writing converts a complex text prompt involving a chain of HSI into simple atomic actions that are used in the pre-visualization stage to generate 3D keyframes. To synthesize plausible human interaction poses in 3D keyframes, we utilize pre-trained 2D inpainting diffusion models to generate plausible 2D human interactions based on view canonicalization, which eliminates the need for multi-view fitting in previous works. We then extend these interactions to 3D using robust iterative optimization, informed by contact cues and reasoning from VLMs. Prompted by these 3D keyframes, the pretrained video diffusion models can better generate consistent long videos with plausible dynamics and affordance in a 3D-aware manner. We are the first to synthesize a long video sequence with a chain of HSI actions without training based on the image references of the scene and character. Experiments demonstrate that our method can generate HSI videos that effectively preserve scene content and character identity with plausible humanscene interaction from a single image scene.

Advances in 3D reconstruction and novel view synthesis have enabled efficient and photorealistic rendering. However, images for reconstruction are still either largely manual or constrained by simple preplanned trajectories. To address this issue, recent works propose generalizable next-best-view planners that do not require online learning. Nevertheless, robustness and performance remain limited across various shapes. Hence, this study introduces Voxel-Face-Aware Hierarchical Next-Best-View Acquisition for Efficient 3D Reconstruction (Hestia1), which addresses the shortcomings of the reinforcement learning-based generalizable approaches for five-degree-of-freedom viewpoint prediction. Hestia systematically improves the planners through four components: a more diverse dataset to promote robustness, a hierarchical structure to manage the high-dimensional continuous action search space, a close-greedy strategy to mitigate spurious correlations, and a face-aware design to avoid overlooking geometry. Experimental results show that Hestia achieves non-marginal improvements, with at least a 4% gain in coverage ratio, while reducing Chamfer Distance by 50% and maintaining real-time inference. In addition, Hestia outperforms prior methods by at least 12% in coverage ratio with a 5-image budget and remains robust to object placement variations. Finally, we demonstrate that Hestia, as a next-best-view planner, is feasible for the real-world application. Our project page is https://johnnylu305.github.io/hestia_web.

Abstract Recent advances in generative modeling have driven significant progress in text‐guided texture synthesis. However, current methods focus on synthesizing texture for single static 3D object, and struggle to handle entire families of shapes, such as those produced by procedural programs. Applying existing methods naively to each procedural shape is too slow to support exploring different parameter configurations at interactive rates, and also results in inconsistent textures across the procedural shapes. To this end, we introduce ProcTex, the first text‐to‐texture system designed for part‐based procedural models. ProcTex enables consistent and real‐time text‐guided texture synthesis for families of shapes, which integrates seamlessly with the interactive design flow of procedural modeling. To ensure consistency, our core approach is to synthesize texture for a template shape from the procedural model, followed by a texture transfer stage to apply the texture to other procedural shapes via solving dense correspondence. To ensure interactiveness, we propose a novel correspondence network and show that dense correspondence can be effectively learned by a neural network for procedural models. We also develop several techniques, including a retexturing pipeline to support structural variation from procedural parameters, and part‐level UV texture map generation for local appearance editing. Extensive experiments on a diverse set of procedural models validate ProcTex's ability to produce high‐quality, visually consistent textures while supporting interactive applications. Code and data are available at: https://github.com/ruiqixu37/ProcTex.git

Despite remarkable progress in image generation models, generating realistic hands remains a persistent challenge due to their complex articulation, varying viewpoints, and frequent occlusions. We present FoundHand, a large-scale domain-specific diffusion model for synthesizing single and dual hand images. To train our model, we introduce FoundHand-10M, a large-scale hand dataset with 2D keypoints and segmentation mask annotations. Our insight is to use 2D hand keypoints as a universal representation that encodes both hand articulation and camera viewpoint. FoundHand learns from image pairs to capture physically plausible hand articulations, natively enables precise control through 2D keypoints, and supports appearance control. Our model exhibits core capabilities that include the ability to repose hands, transfer hand appearance, and even synthesize novel views. This leads to zero-shot capabilities for fixing malformed hands in previously generated images, or synthesizing hand video sequences. We present extensive experiments and evaluations that demonstrate state-of-the-art performance of our method.

Understanding bimanual human hand activities is a critical problem in AI and robotics. We cannot build large models of bimanual activities because existing datasets lack the scale, coverage of diverse hand activities, and detailed annotations. We introduce GigaHands, a massive annotated dataset capturing 34 hours of bimanual hand activities from 56 subjects and 417 objects, totaling 14k motion clips derived from 183 million frames paired with 84k text annotations. Our markerless capture setup and data acquisition protocol enable fully automatic 3D hand and object estimation while minimizing the effort required for text annotation. The scale and diversity of GigaHands enable broad applications, including text-driven action synthesis, hand motion captioning, and dynamic radiance field reconstruction.

3D Gaussian Splatting (3DGS) has demonstrated superior quality in modeling 3D objects and scenes. However, generating 3DGS remains challenging due to their discrete, unstructured, and permutation-invariant nature. In this work, we present a simple yet effective method to overcome these challenges. We utilize spherical mapping to transform 3DGS into a structured 2D representation, termed UVGS. UVGS can be viewed as multi-channel images, with feature dimensions as a concatenation of Gaussian attributes such as position, scale, color, opacity, and rotation. We further find that these heterogeneous features can be compressed into a lower-dimensional (e.g., 3-channel) shared feature space using a carefully designed multi-branch network. The compressed UVGS can be treated as typical RGB images. Remarkably, we discover that typical VAEs trained with latent diffusion models can directly generalize to this new representation without additional training. Our novel representation makes it effortless to leverage foundational 2D models, such as diffusion models, to directly model 3DGS. Additionally, one can simply increase the 2D UV resolution to accommodate more Gaussians, making UVGS a scalable solution compared to typical 3D backbones. This approach immediately unlocks various novel generation applications of 3DGS by inherently utilizing the already developed superior 2D generation capabilities. In our experiments, we demonstrate various unconditional, conditional generation, and inpainting applications of 3DGS based on diffusion models, which were previously non-trivial.

This paper introduces MotionGlot, a model that can generate motion across multiple embodiments with different action dimensions, such as quadruped robots and human bodies. By leveraging the well-established training procedures commonly used in large language models (LLMs), we introduce an instruction-tuning template specifically designed for motionrelated tasks. Our approach demonstrates that the principles underlying LLM training can be successfully adapted to learn a wide range of motion generation tasks across multiple embodiments with different action dimensions. We demonstrate the various abilities of MotionGlot on a set of 6 tasks and report an average improvement of$\mathbf{3 5. 3 \%}$across tasks. Additionally, we contribute two new datasets: (1) a dataset of expert-controlled quadruped locomotion with approximately 48,000 trajectories paired with direction-based text annotations, and (2) a dataset of over 23,000 situational text prompts for human motion generation tasks. Finally, we conduct hardware experiments to validate the capabilities of our system in real-world applications.

Dual-arm manipulation is an area of growing interest in the robotics community. Enabling robots to perform tasks that require the coordinated use of two arms, is essential for complex manipulation tasks such as handling large objects, assembling components, and performing human-like interactions. However, achieving effective dual-arm manipulation is challenging due to the need for precise coordination, dynamic adaptability, and the ability to manage interaction forces between the arms and the objects being manipulated. We propose a novel pipeline that combines the advantages of policy learning based on environment feedback and gradient-based optimization to learn controller gains required for the control outputs. This allows the robotic system to dynamically modulate its impedance in response to task demands, ensuring stability and dexterity in dual-arm operations. We evaluate our pipeline on a trajectory-tracking task involving a variety of large, complex objects with different masses and geometries. The performance is then compared to three other established methods for controlling dual-arm robots, demonstrating superior results. Project page: https://dualarmvil.github.io/Dual-Arm-VIL/

Object 6D pose estimation is a critical challenge in robotics, particularly for manipulation tasks. While prior research combining visual and tactile (visuotactile) information has shown promise, these approaches often struggle with generalization due to the limited availability of visuotactile data. In this paper, we introduce ViTa-Zero, a zero-shot visuotactile pose estimation framework. Our key innovation lies in leveraging a visual model as its backbone and performing feasibility checking and test-time optimization based on physical constraints derived from tactile and proprioceptive observations. Specifically, we model the gripper-object interaction as a spring-mass system, where tactile sensors induce attractive forces, and proprioception generates repulsive forces. We validate our framework through experiments on a real-world robot setup, demonstrating its effectiveness across representative visual backbones and manipulation scenarios, including grasping, object picking, and bimanual handover. Compared to the visual models, our approach overcomes some drastic failure modes while tracking the in-hand object pose. In our experiments, our approach shows an average increase of 55% in AUC of ADD-S and 60% in ADD, along with an 80% lower position error compared to FoundationPose.

We introduce EgoSonics, a method to generate semanti-cally meaningful and synchronized audio tracks conditioned on silent egocentric videos. Generating audio for silent ego-centric videos could open new applications in virtual reality, assistive technologies, or for augmenting existing datasets. Existing work has been limited to domains like speech, mu-sic, or impact sounds and cannot capture the broad range of audio frequencies found in egocentric videos. EgoSonics ad-dresses these limitations by building on the strengths of latent diffusion models for conditioned audio synthesis. We first encode and process paired audio-video data to make them suitable for generation. The encoded data is then used to train a model that can generate an audio track that captures the semantics of the input video. Our proposed SyncroNet builds on top of ControlNet to provide control signals that enables generation of temporally-synchronized audio. Exten-sive evaluations and a comprehensive user study show that our model outperforms existing work in audio quality, and in our proposed synchronization evaluation method. Fur-thermore, we demonstrate downstream applications of our model in improving video summarization.

The success of image generative models has enabled us to build methods that can edit images based on text or other user input. However, these methods are imprecise, require additional information, or are limited to only 2D image edits. We present GeoDiffuser, a zero-shot optimization-based method that unifies common 2D and 3D image-based object editing capabilities into a single method. Our key insight is to view image editing operations as geometric transformations. We show that these transformations can be directly incorporated into the attention layers in diffusion models to implicitly perform editing operations. Our training-free optimization method uses an objective function that seeks to preserve object style but generate plausible images, for instance with accurate lighting and shadows. It also inpaints disoccluded parts of the image where the object was originally located. Given a natural image and user input, we segment the foreground object [27] and estimate a corresponding transform which is used by our optimization approach for editing. Figure 1 shows that GeoDiffuser can perform common 2D and 3D edits like object translation, 3D rotation, and removal. We present quantitative results, including a perceptual study, that shows how our approach is better than existing methods.

Advances in neural fields are enabling high-fidelity capture of the shape and appearance of dynamic 3D scenes. However, their capabilities lag behind those offered by conventional representations such as 2D videos because of algorithmic challenges and the lack of large-scale multi-view real-world datasets. We address the dataset limitation with DiVa-360, a real-world 360° dynamic visual dataset that contains synchronized high-resolution and long-duration multi-view video sequences of table-scale scenes captured using a customized low-cost system with 53 cameras. It contains 21 object-centric sequences categorized by different motion types, 25 intricate hand-object interaction sequences, and 8 long-duration sequences for a total of 17.4 M image frames. In addition, we provide foreground-background segmentation masks, synchronized audio, and text descriptions. We benchmark the state-of-the-art dynamic neural field methods on DiVa-360 and provide insights about existing methods and future challenges on long-duration neural field capture.

Understanding how we grasp objects with our hands has important applications in areas like robotics and mixed re-ality. However, this challenging problem requires accurate modeling of the contact between hands and objects. To capture grasps, existing methods use skeletons, meshes, or parametric models that does not represent hand shape accu-rately resulting in inaccurate contacts. We present MANUS, a method for Markerless Hand-Object Grasp Capture using Articulated 3D Gaussians. We build a novel articulated 3D Gaussians representation that extends 3D Gaussian splatting [29] for high-fidelity representation of articulating hands. Since our representation uses Gaussian primitives optimized from the multi-view pixel-aligned losses, it enables us to efficiently and accurately estimate contacts between the hand and the object. For the most accurate results, our method requires tens of camera views that current datasets do not provide. We therefore build MANUS-Grasps, a new dataset that contains hand-object grasps viewed from 50+ cameras across 30+ scenes, 3 subjects, and comprising over 7M frames. In addition to extensive qualitative results, we also show that our method outper-forms others on a quantitative contact evaluation method that uses paint transfer from the object to the hand.

Efficiently generating grasp poses tailored to specific regions of an object is vital for various robotic manipulation tasks, especially in a dual-arm setup. This scenario presents a significant challenge due to the complex geometries involved, requiring a deep understanding of the local geometry to generate grasps efficiently on the specified constrained regions. Existing methods only explore settings involving table-top/small objects and require augmented datasets to train, limiting their performance on complex objects. We propose CGDF: Constrained Grasp Diffusion Fields, a diffusion-based grasp generative model that generalizes to objects with arbitrary geometries, as well as generates dense grasps on the target regions. CGDF uses a part-guided diffusion approach that enables it to get high sample efficiency in constrained grasping without explicitly training on massive constraint-augmented datasets. We provide qualitative and quantitative comparisons using analytical metrics and in simulation, in both unconstrained and constrained settings to show that our method can generalize to generate stable grasps on complex objects, especially useful for dual-arm manipulation settings, while existing methods struggle to do so. More results, code and an extended version of the paper can be found on the project page: https://constrained-grasp-diffusion.github.io/

Coordinate-based implicit neural networks, or neural fields, have emerged as useful representations of shape and appearance in 3D computer vision. Despite advances, however, it remains challenging to build neural fields for categories of objects without datasets like ShapeNet that provide “canonicalized” object instances that are consistently aligned for their 3D position and orientation (pose). We present Canonical Field Network (CaFi-Net), a self-supervised method to canonicalize the 3D pose of instances from an object category represented as neural fields, specifically neural radiance fields (NeRFs). CaFi-Net directly learns from continuous and noisy radiance fields using a Siamese network architecture that is designed to extract equivariant field features for category-level canonicalization. During inference, our method takes pre-trained neural radiance fields of novel object instances at arbitrary 3D pose and estimates a canonical field with consistent 3D pose across the entire category. Extensive experiments on a new dataset of 1300 NeRF models across 13 object categories show that our method matches or exceeds the performance of 3D point cloud-based methods.

Recent works have demonstrated that natural language can be used to generate and edit 3D shapes. However, these methods generate shapes with limited fidelity and diversity. We introduce CLIP-Sculptor, a method to address these constraints by producing high-fidelity and diverse 3D shapes without the need for (text, shape) pairs during training. CLIP-Sculptor achieves this in a multi-resolution approach that first generates in a low-dimensional latent space and then upscales to a higher resolution for improved shape fidelity. For improved shape diversity, we use a discrete latent space which is modeled using a transformer conditioned on CLIP's image-text embedding space. We also present a novel variant of classifier-free guidance, which improves the accuracy-diversity trade-off. Finally, we perform extensive experiments demonstrating that CLIP-Sculptor outperforms state-of-the-art baselines.

Humans universally dislike the task of cleaning up a messy room. If machines were to help us with this task, they must understand human criteria for regular arrangements, such as several types of symmetry, co-linearity or co-circularity, spacing uniformity in linear or circular patterns, and further inter-object relationships that relate to style and functionality. Previous approaches for this task relied on human input to explicitly specify goal state, or synthesized scenes from scratch - but such methods do not address the rearrangement of existing messy scenes without providing a goal state. In this paper, we present LEGO-Net, a data-driven transformer-based iterative method for LEarning reGular rearrangement of Objects in messy rooms. LEGO-Net is partly inspired by diffusion models - it starts with an initial messy state and iteratively “de-noises” the position and orientation of objects to a regular state while reducing distance traveled. Given randomly perturbed object positions and orientations in an existing dataset of professionally-arranged scenes, our method is trained to recover a regular rearrangement. Results demonstrate that our method is able to reliably rearrange room scenes and outperform other methods. We additionally propose a metric for evaluating regularity in room arrangements using number-theoretic machinery.

Neural Radiance Field (NeRF) approaches learn the underlying 3D representation of a scene and generate photo-realistic novel views with high fidelity. However, most proposed settings concentrate on modelling a single object or a single level of a scene. However, in the real world, we may capture a scene at multiple levels, resulting in a layered capture. For example, tourists usually capture a monument’s exterior structure before capturing the inner structure. Modelling such scenes in 3D with seamless switching between levels can drastically improve immersive experiences. However, most existing techniques struggle in modelling such scenes. We propose Strata-NeRF, a single neural radiance field that implicitly captures a scene with multiple levels. Strata-NeRF achieves this by conditioning the NeRFs on Vector Quantized (VQ) latent representations which allow sudden changes in scene structure. We evaluate the effectiveness of our approach in multi-layered synthetic dataset comprising diverse scenes and then further validate its generalization on the real-world RealEstate10K dataset. We find that Strata-NeRF effectively captures stratified scenes, minimizes artifacts, and synthesizes high-fidelity views compared to existing approaches. https://ankitatiisc.github.io/Strata-NeRF/

From video, we reconstruct a neural volume that captures time-varying color, density, scene flow, semantics, and attention information. The semantics and attention let us identify salient foreground objects separately from the background across spacetime. To mitigate low resolution semantic and attention features, we compute pyramids that trade detail with whole-image context. After optimization, we perform a saliency-aware clustering to decompose the scene. To evaluate real-world scenes, we annotate object masks in the NVIDIA Dynamic Scene and DyCheck datasets. We demonstrate that this method can decompose dynamic scenes in an unsupervised way with competitive performance to a supervised method, and that it improves foreground/background segmentation over recent static/dynamic split methods. Project webpage: https://visual.cs.brown.edu/saff

Recovering full 3D shapes from partial observations is a challenging task that has been extensively addressed in the computer vision community. Many deep learning methods tackle this problem by training 3D shape generation networks to learn a prior over the full 3D shapes. In this training regime, the methods expect the inputs to be in a fixed canonical form, without which they fail to learn a valid prior over the 3D shapes. We propose SCARP, a model that performs Shape C ompletion in ARbitrary Poses. Given a partial pointcloud of an object, SCARP learns a disentangled feature representation of pose and shape by relying on rotationally equivariant pose features and geometric shape features trained using a multi-tasking objective. Unlike existing methods that depend on an external canonicalization method, SCARP performs canonicalization, pose estimation, and shape completion in a single network, improving the performance by 45% over the existing baselines. In this work, we use SCARP for improving grasp proposals on tabletop objects. By completing partial tabletop objects directly in their observed poses, SCARP enables a SOTA grasp proposal network improve their proposals by 71.2% on partial shapes. Project page: https://bipashasen.github.io/scarp

Neural Radiance Fields (NeRF) have become an increasingly popular representation to capture high-quality appearance and shape of scenes and objects. However, learning generalizable NeRF priors over categories of scenes or objects has been challenging due to the high dimensionality of network weight space. To address the limitations of existing work on generalization, multi-view consistency and to improve quality, we propose HyP-NeRF, a latent conditioning method for learning generalizable category-level NeRF priors using hypernetworks. Rather than using hypernetworks to estimate only the weights of a NeRF, we estimate both the weights and the multi-resolution hash encodings resulting in significant quality gains. To improve quality even further, we incorporate a denoise and finetune strategy that denoises images rendered from NeRFs estimated by the hypernetwork and finetunes it while retaining multiview consistency. These improvements enable us to use HyP-NeRF as a generalizable prior for multiple downstream tasks including NeRF reconstruction from single-view or cluttered scenes and text-to-NeRF. We provide qualitative comparisons and evaluate HyP-NeRF on three tasks: generalization, compression, and retrieval, demonstrating our state-of-the-art results.

Progress in 3D object understanding has relied on manually “canonicalized” shape datasets that contain instances with consistent position and orientation (3D pose). This has made it hard to generalize these methods to in-the-wild shapes, e.g., from internet model collections or depth sensors. ConDor is a self-supervised method that learns to Canonicalize the 3D orientation and position for full and partial 3D point clouds. We build on top of Tensor Field Networks (TFNs), a class of permutation- and rotation-equivariant, and translation-invariant 3D networks. During inference, our method takes an unseen full or partial 3D point cloud at an arbitrary pose and outputs an equivariant canonical pose. During training, this network uses self-supervision losses to learn the canonical pose from an un-canonicalized collection of full and partial 3D point clouds. ConDor can also learn to consistently co-segment object parts without any supervision. Extensive quantitative results on four new metrics show that our approach out-performs existing methods while enabling new applications such as operation on depth images and annotation transfer.

We present ShapeCrafter, a neural network for recursive text-conditioned 3D shape generation. Existing methods to generate text-conditioned 3D shapes consume an entire text prompt to generate a 3D shape in a single step. However, humans tend to describe shapes recursively---we may start with an initial description and progressively add details based on intermediate results. To capture this recursive process, we introduce a method to generate a 3D shape distribution, conditioned on an initial phrase, that gradually evolves as more phrases are added. Since existing datasets are insufficient for training this approach, we present Text2Shape++, a large dataset of 369K shape--text pairs that supports recursive shape generation. To capture local details that are often used to refine shape descriptions, we build on top of vector-quantized deep implicit functions that generate a distribution of high-quality shapes. Results show that our method can generate shapes consistent with text descriptions, and shapes evolve gradually as more phrases are added. Our method supports shape editing, extrapolation, and can enable new applications in human--machine collaboration for creative design.

Abstract Recent advances in machine learning have led to increased interest in solving visual computing problems using methods that employ coordinate‐based neural networks. These methods, which we call neural fields , parameterize physical properties of scenes or objects across space and time. They have seen widespread success in problems such as 3D shape and image synthesis, animation of human bodies, 3D reconstruction, and pose estimation. Rapid progress has led to numerous papers, but a consolidation of the discovered knowledge has not yet emerged. We provide context, mathematical grounding, and a review of over 250 papers in the literature on neural fields. In Part I , we focus on neural field techniques by identifying common components of neural field methods, including different conditioning, representation, forward map, architecture, and manipulation methods. In Part II , we focus on applications of neural fields to different problems in visual computing, and beyond (e.g., robotics, audio). Our review shows the breadth of topics already covered in visual computing, both historically and in current incarnations, and highlights the improved quality, flexibility, and capability brought by neural field methods. Finally, we present a companion website that acts as a living database that can be continually updated by the community.

We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of temporal pose and shape. Though substantial progress has been made in estimating 3D human motion and shape from dynamic observations, recovering plausible pose sequences in the presence of noise and occlusions remains a challenge. For this purpose, we propose an expressive generative model in the form of a conditional variational autoencoder, which learns a distribution of the change in pose at each step of a motion sequence. Furthermore, we introduce a flexible optimization-based approach that leverages HuMoR as a motion prior to robustly estimate plausible pose and shape from ambiguous observations. Through extensive evaluations, we demonstrate that our model generalizes to diverse motions and body shapes after training on a large motion capture dataset, and enables motion reconstruction from multiple input modalities including 3D keypoints and RGB(-D) videos. See the project page at geometry.stanford.edu/projects/humor.

We present DRACO, a method for Dense Reconstruction And Canonicalization of Object shape from one or more RGB images. Canonical shape reconstruction— estimating 3D object shape in a coordinate space canonicalized for scale, rotation, and translation parameters—is an emerging paradigm that holds promise for a multitude of robotic applications. Prior approaches either rely on painstakingly gathered dense 3D supervision, or produce only sparse canonical representations, limiting real-world applicability. DRACO performs dense canonicalization using only weak supervision in the form of camera poses and semantic keypoints at train time. During inference, DRACO predicts dense object-centric depth maps in a canonical coordinate-space, solely using one or more RGB images of an object. Extensive experiments on canonical shape reconstruction and pose estimation show that DRACO is competitive or superior to fully-supervised methods.

We seek to learn a representation on a large annotated data source that generalizes to a target domain using limited new supervision. Many prior approaches to this problem have focused on learning "disentangled" representations so that as individual factors vary in a new domain, only a portion of the representation need be updated. In this work, we seek the generalization power of disentangled representations, but relax the requirement of explicit latent disentanglement and instead encourage linearity of individual factors of variation by requiring them to be manipulable by learned linear transformations. We dub these transformations latent canonicalizers, as they aim to modify the value of a factor to a pre-determined (but arbitrary) canonical value (e.g., recoloring the image foreground to black). By creating simple simulators with pre-specified factors of variation to roughly approximate datasets such as SVHN and ImageNet, we demonstrate experimentally that our method helps reduce the number of observations needed to generalize to a similar target domain when compared to a number of supervised baselines.

The majority of descriptor-based methods for geometric processing of non-rigid shape rely on hand-crafted descriptors. Recently, learning-based techniques have been shown effective, achieving state-of-the-art results in a variety of tasks. Yet, even though these methods can in principle work directly on raw data, most methods still rely on handcrafted descriptors at the input layer. In this work, we wish to challenge this practice and use a neural network to learn descriptors directly from the raw mesh. To this end, we introduce two modules into our neural architecture. The first is a local reference frame (LRF) used to explicitly make the features invariant to rigid transformations. The second is continuous convolution kernels that provide robustness to sampling. We show the efficacy of our proposed network in learning on raw meshes using two cornerstone tasks: shape matching, and human body parts segmentation. Our results show superior results over baseline methods that use handcrafted descriptors.

We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects. Our goal is to enable information aggregation over time and the interrogation of object state at any spatiotemporal neighborhood in the past, observed or not. Different from previous work, CaSPR learns representations that support spacetime continuity, are robust to variable and irregularly spacetime-sampled point clouds, and generalize to unseen object instances. Our approach divides the problem into two subtasks. First, we explicitly encode time by mapping an input point cloud sequence to a spatiotemporally-canonicalized object space. We then leverage this canonicalization to learn a spatiotemporal latent representation using neural ordinary differential equations and a generative model of dynamically evolving shapes using continuous normalizing flows. We demonstrate the effectiveness of our method on several applications including shape reconstruction, camera pose estimation, continuous spatiotemporal sequence reconstruction, and correspondence estimation from irregularly or intermittently sampled observations.

Machines that can predict the effect of physical interactions on the dynamics of previously unseen object instances are important for creating better robots and interactive virtual worlds. In this work, we focus on predicting the dynamics of 3D objects on a plane that have just been subjected to an impulsive force. In particular, we predict the changes in state-3D position, rotation, velocities, and stability. Different from previous work, our approach can generalize dynamics predictions to object shapes and initial conditions that were unseen during training. Our method takes the 3D object's shape as a point cloud and its initial linear and angular velocities as input. We extract shape features and use a recurrent neural network to predict the full change in state at each time step. Our model can support training with data from both a physics engine or the real world. Experiments show that we can accurately predict the changes in state for unseen object geometries and initial conditions.

The goal of this paper is to estimate the 6D pose and dimensions of unseen object instances in an RGB-D image. Contrary to "instance-level'' 6D pose estimation tasks, our problem assumes that no exact object CAD models are available during either training or testing time. To handle different and unseen object instances in a given category, we introduce a Normalized Object Coordinate Space (NOCS)-a shared canonical representation for all possible object instances within a category. Our region-based neural network is then trained to directly infer the correspondence from observed pixels to this shared object representation (NOCS) along with other object information such as class label and instance mask. These predictions can be combined with the depth map to jointly estimate the metric 6D pose and dimensions of multiple objects in a cluttered scene. To train our network, we present a new context-aware technique to generate large amounts of fully annotated mixed reality data. To further improve our model and evaluate its performance on real data, we also provide a fully annotated real-world dataset with large environment and instance variation. Extensive experiments demonstrate that the proposed method is able to robustly estimate the pose and size of unseen object instances in real environments while also achieving state-of-the-art performance on standard 6D pose estimation benchmarks.

We investigate the problem of learning category-specific 3D shape reconstruction from a variable number of RGB views of previously unobserved object instances. Most approaches for multiview shape reconstruction operate on sparse shape representations, or assume a fixed number of views. We present a method that can estimate dense 3D shape, and aggregate shape across multiple and varying number of input views. Given a single input view of an object instance, we propose a representation that encodes the dense shape of the visible object surface as well as the surface behind line of sight occluded by the visible surface. When multiple input views are available, the shape representation is designed to be aggregated into a single 3D shape using an inexpensive union operation. We train a 2D CNN to learn to predict this representation from a variable number of views (1 or more). We further aggregate multiview information by using permutation equivariant layers that promote order-agnostic view information exchange at the feature level. Experiments show that our approach is able to produce dense 3D reconstructions of objects that improve in quality as more views are added.

Abstract Creating dynamic virtual environments consisting of humans interacting with objects is a fundamental problem in computer graphics. While it is well‐accepted that agent interactions play an essential role in synthesizing such scenes, most extant techniques exclusively focus on static scenes, leaving the dynamic component out. In this paper, we present a generative model to synthesize plausible multi‐step dynamic human‐object interactions. Generating multi‐step interactions is challenging since the space of such interactions is exponential in the number of objects, activities, and time steps. We propose to handle this combinatorial complexity by learning a lower dimensional space of plausible human‐object interactions. We use action plots to represent interactions as a sequence of discrete actions along with the participating objects and their states. To build action plots, we present an automatic method that uses state‐of‐the‐art computer vision techniques on RGB videos in order to detect individual objects and their states, extract the involved hands, and recognize the actions performed. The action plots are built from observing videos of everyday activities and are used to train a generative model based on a Recurrent Neural Network (RNN). The network learns the causal dependencies and constraints between individual actions and can be used to generate novel and diverse multi‐step human‐object interactions. Our representation and generative model allows new capabilities in a variety of applications such as interaction prediction, animation synthesis, and motion planning for a real robotic agent.

We propose a new single-shot method for multi-person 3D pose estimation in general scenes from a monocular RGB camera. Our approach uses novel occlusion-robust pose-maps (ORPM) which enable full body pose inference even under strong partial occlusions by other people and objects in the scene. ORPM outputs a fixed number of maps which encode the 3D joint locations of all people in the scene. Body part associations [8] allow us to infer 3D pose for an arbitrary number of people without explicit bounding box prediction. To train our approach we introduce MuCo-3DHP, the first large scale training data set showing real images of sophisticated multi-person interactions and occlusions. We synthesize a large corpus of multi-person images by compositing images of individual people (with ground truth from mutli-view performance capture). We evaluate our method on our new challenging 3D annotated multi-person test set MuPoTs-3D where we achieve state-of-the-art performance. To further stimulate research in multi-person 3D pose estimation, we will make our new datasets, and associated code publicly available for research purposes.

We address the highly challenging problem of real-time 3D hand tracking based on a monocular RGB-only sequence. Our tracking method combines a convolutional neural network with a kinematic 3D hand model, such that it generalizes well to unseen data, is robust to occlusions and varying camera viewpoints, and leads to anatomically plausible as well as temporally smooth hand motions. For training our CNN we propose a novel approach for the synthetic generation of training data that is based on a geometrically consistent image-to-image translation network. To be more specific, we use a neural network that translates synthetic images to "real" images, such that the so-generated images follow the same statistical distribution as real-world hand images. For training this translation network we combine an adversarial loss and a cycle-consistency loss with a geometric consistency loss in order to preserve geometric properties (such as hand pose) during translation. We demonstrate that our hand tracking system outperforms the current state-of-the-art on challenging RGB-only footage.

This paper contributes a novel sensing approach to support on- and above-skin finger input for interaction on the move. WatchSense uses a depth sensor embedded in a wearable device to expand the input space to neighboring areas of skin and the space above it. Our approach addresses challenging camera-based tracking conditions, such as oblique viewing angles and occlusions. It can accurately detect fingertips, their locations, and whether they are touching the skin or hovering above it. It extends previous work that supported either mid-air or multitouch input by simultaneously supporting both. We demonstrate feasibility with a compact, wearable prototype attached to a user's forearm (simulating an integrated depth sensor). Our prototype---which runs in real-time on consumer mobile devices---enables a 3D input space on the back of the hand. We evaluated the accuracy and robustness of the approach in a user study. We also show how WatchSense increases the expressiveness of input by interweaving mid-air and multitouch for several interactive applications.

We present an approach for real-time, robust and accurate hand pose estimation from moving egocentric RGB-D cameras in cluttered real environments. Existing methods typically fail for hand-object interactions in cluttered scenes imaged from egocentric viewpoints-common for virtual or augmented reality applications. Our approach uses two subsequently applied Convolutional Neural Networks (CNNs) to localize the hand and regress 3D joint locations. Hand localization is achieved by using a CNN to estimate the 2D position of the hand center in the input, even in the presence of clutter and occlusions. The localized hand position, together with the corresponding input depth value, is used to generate a normalized cropped image that is fed into a second CNN to regress relative 3D hand joint locations in real time. For added accuracy, robustness and temporal stability, we refine the pose estimates using a kinematic pose tracking energy. To train the CNNs, we introduce a new photorealistic dataset that uses a merged reality approach to capture and synthesize large amounts of annotated data of natural hand interaction in cluttered scenes. Through quantitative and qualitative evaluation, we show that our method is robust to self-occlusion and occlusions by objects, particularly in moving egocentric perspectives.

We present the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera. Our method combines a new convolutional neural network (CNN) based pose regressor with kinematic skeleton fitting. Our novel fully-convolutional pose formulation regresses 2D and 3D joint positions jointly in real time and does not require tightly cropped input frames. A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleton. This makes our approach the first monocular RGB method usable in real-time applications such as 3D character control---thus far, the only monocular methods for such applications employed specialized RGB-D cameras. Our method's accuracy is quantitatively on par with the best offline 3D monocular RGB pose estimation methods. Our results are qualitatively comparable to, and sometimes better than, results from monocular RGB-D approaches, such as the Kinect. However, we show that our approach is more broadly applicable than RGB-D solutions, i.e., it works for outdoor scenes, community videos, and low quality commodity RGB cameras.

This paper investigates an emerging input method enabled by progress in hand tracking: input by free motion of fingers. The method is expressive, potentially fast, and usable across many settings as it does not insist on physical contact or visual feedback. Our goal is to inform the design of high-performance input methods by providing detailed analysis of the performance and anatomical characteristics of finger motion. We conducted an experiment using a commercially available sensor to report on the speed, accuracy, individuation, movement ranges, and individual differences of each finger. Findings show differences of up to 50% in movement times and provide indices quantifying the individuation of single fingers. We apply our findings to text entry by computational optimization of multi-finger gestures in mid-air. To this end, we define a novel objective function that considers performance, anatomical factors, and learnability. First investigations of one optimization case show entry rates of 22 words per minute (WPM). We conclude with a critical discussion of the limitations posed by human factors and performance characteristics of existing markerless hand trackers.

Markerless tracking of hands and fingers is a promising enabler for human-computer interaction. However, adoption has been limited because of tracking inaccuracies, incomplete coverage of motions, low framerate, complex camera setups, and high computational requirements. In this paper, we present a fast method for accurately tracking rapid and complex articulations of the hand using a single depth camera. Our algorithm uses a novel detectionguided optimization strategy that increases the robustness and speed of pose estimation. In the detection step, a randomized decision forest classifies pixels into parts of the hand. In the optimization step, a novel objective function combines the detected part labels and a Gaussian mixture representation of the depth to estimate a pose that best fits the depth. Our approach needs comparably less computational resources which makes it extremely fast (50 fps without GPU support). The approach also supports varying static, or moving, camera-to-scene arrangements. We show the benefits of our method by evaluating on public datasets and comparing against previous work.

Real-time marker-less hand tracking is of increasing importance in human-computer interaction. Robust and accurate tracking of arbitrary hand motion is a challenging problem due to the many degrees of freedom, frequent self-occlusions, fast motions, and uniform skin color. In this paper, we propose a new approach that tracks the full skeleton motion of the hand from multiple RGB cameras in real-time. The main contributions include a new generative tracking method which employs an implicit hand shape representation based on Sum of Anisotropic Gaussians (SAG), and a pose fitting energy that is smooth and analytically differentiable making fast gradient based pose optimization possible. This shape representation, together with a full perspective projection model, enables more accurate hand modeling than a related baseline method from literature. Our method achieves better accuracy than previous methods and runs at 25 fps. We show these improvements both qualitatively and quantitatively on publicly available datasets.

Tracking the articulated 3D motion of the hand has important applications, for example, in human-computer interaction and teleoperation. We present a novel method that can capture a broad range of articulated hand motions at interactive rates. Our hybrid approach combines, in a voting scheme, a discriminative, part-based pose retrieval method with a generative pose estimation method based on local optimization. Color information from a multi-view RGB camera setup along with a person-specific hand model are used by the generative method to find the pose that best explains the observed images. In parallel, our discriminative pose estimation method uses fingertips detected on depth data to estimate a complete or partial pose of the hand by adopting a part-based pose retrieval strategy. This part-based strategy helps reduce the search space drastically in comparison to a global pose retrieval strategy. Quantitative results show that our method achieves state-of-the-art accuracy on challenging sequences and a near-real time performance of 10 fps on a desktop computer.

In-vehicle contextual augmented reality (I-CAR) has the potential to provide novel visual feedback to drivers for an enhanced driving experience. To enable I-CAR, we present a parametrized road trench model (RTM) for dynamically extracting display surfaces from a driver's point of view that is adaptable to constantly changing road curvature and intersections. We use computer vision algorithms to analyze and extract road features that are used to estimate the parameters of the RTM. GPS coordinates are used to quickly compute lighting parameters for shading and shadows. Novel driver-based applications that use the RTM are presented.