We consider the problem of 3D shape recovery from ultra-fast motion-blurred images. While 3D reconstruction from static images has been extensively studied, recovering geometry from extreme motion-blurred images remains challenging. Such scenarios frequently occur in both natural and industrial settings, such as fast-moving objects in sports (e.g., balls) or rotating machinery, where rapid motion distorts object appearance and makes traditional 3D reconstruction techniques like Multi-View Stereo (MVS) ineffective. In this paper, we propose a novel inverse rendering approach for shape recovery from ultra-fast motion-blurred images. While conventional rendering techniques typically synthesize blur by averaging across multiple frames, we identify a major computational bottleneck in the repeated computation of barycentric weights. To address this, we propose a fast barycentric coordinate solver, which significantly reduces computational overhead and achieves a speedup of up to$4.57 \times$, enabling efficient and photorealistic simulation of high-speed motion. Crucially, our method is fully differentiable, allowing gradients to propagate from rendered images to the underlying 3D shape, thereby facilitating shape recovery through inverse rendering. We validate our approach on two representative motion types: rapid translation and rotation. Experimental results demonstrate that our method enables efficient and realistic modeling of ultra-fast moving objects in the forward simulation. Moreover, it successfully recovers 3D shapes from 2D imagery of objects undergoing extreme translational and rotational motion, advancing the boundaries of vision-based 3D reconstruction.

Diffusion models have emerged as powerful tools for solving inverse problems due to their exceptional ability to model complex prior distributions. However, existing methods predominantly assume known forward operators (i.e., non-blind), limiting their applicability in practical settings where acquiring such operators is costly. Additionally, many current approaches rely on pixel-space diffusion models, leaving the potential of more powerful latent diffusion models (LDMs) underexplored. In this paper, we introduce LatentDEM, an innovative technique that addresses more challenging blind inverse problems using latent diffusion priors. At the core of our method is solving blind inverse problems within an iterative Expectation-Maximization (EM) framework: (1) the E-step recovers clean images from corrupted observations using LDM priors and a known forward model, and (2) the M-step estimates the forward operator based on the recovered images. Additionally, we propose two novel optimization techniques tailored for LDM priors and EM frameworks, yielding more accurate and efficient blind inversion results. As a general framework, LatentDEM supports both linear and non-linear inverse problems. Beyond common 2D image restoration tasks, it enables new capabilities in non-linear 3D inverse rendering problems. We validate LatentDEM's performance on representative 2D blind deblurring and 3D pose-free sparse-view reconstruction tasks, demonstrating its superior efficacy over prior arts. The project page can be found at https://ai4imaging.github.io/latentdem/.

We consider the problem of adding dynamic rain effects to in-the-wild scenes in a physically-correct manner. Recent advances in scene modeling have made significant progress, with NeRF and Gaussian Splatting techniques emerging as powerful tools for reconstructing complex scenes. However, while effective for novel view synthesis, these methods typically struggle with challenging scene editing tasks, such as physics-based rain simulation. In contrast, traditional physics-based simulations can generate realistic rain effects, such as raindrops and splashes, but they often rely on skilled artists to carefully set up high-fidelity scenes. This process lacks flexibility and scalability, limiting its applicability to broader, open-world environments. In this work, we introduce RainyGS, a novel approach that leverages the strengths of both physics-based modeling and Gaussian Splatting to generate photorealistic, dynamic rain effects in open-world scenes with physical accuracy. At the core of our method is the integration of physically-based raindrop and shallow water simulation techniques within the fast Gaussian Splatting rendering framework, enabling realistic and efficient simulations of raindrop behavior, splashes, and reflections. Our method supports synthesizing rain effects at over 30 fps, offering users flexible control over rain intensity—from light drizzles to heavy downpours. We demonstrate that RainyGS performs effectively for both real-world outdoor scenes and large-scale driving scenarios, delivering more photorealistic and physically-accurate rain effects compared to state-of-the-art methods. Project page can be found at https://pku-vcl-geometry.github.io/RainyGS/.

3D object canonicalization is a fundamental task, essential for various downstream tasks. Existing methods rely on either cumbersome manual processes or priors learned from extensive, per- category training samples. Real- world datasets, however, often exhibit long- tail distributions, challenging existing learning- based methods, especially in categories with limited samples. We address this by introducing the first one- shot category- level object canonicalization framework that operates under arbitrary poses, requiring only a single canonical model as a reference (the "prior model") for each category. To canonicalize any object, our framework first extracts semantic cues with large language models (LLMs) and vision- language models (VLMs) to establish correspondences with the prior model. We introduce a novel joint energy function to enforce geometric and semantic consistency, aligning object orientations precisely despite significant shape variations. Moreover, we adopt a support- plane strategy to reduce search space for initial poses and utilize a semantic relationship map to select the canonical pose from multiple hypotheses. Extensive experiments on multiple datasets demonstrate that our framework achieves state- of- the- art performance and validates key design choices. Using our framework, we create the Canonical Objaverse Dataset (COD), canonicalizing 32K samples in the Objaverse-LVIS dataset, underscoring the effectiveness of our framework on handling large- scale datasets. Project page at https://github.com/JinLi998/CanonObjaverseDataset

Diffusion models have demonstrated exceptional ability in modeling complex image distributions, making them versatile plug-and-play priors for solving imaging inverse problems. However, their reliance on large-scale clean datasets for training limits their applicability in scenarios where acquiring clean data is costly or impractical. Recent approaches have attempted to learn diffusion models directly from corrupted measurements, but these methods either lack theoretical convergence guarantees or are restricted to specific types of data corruption. In this paper, we propose a principled expectation-maximization (EM) framework that iteratively learns diffusion models from noisy data with arbitrary corruption types. Our framework employs a plug-and-play Monte Carlo method to accurately estimate clean images from noisy measurements, followed by training the diffusion model using the reconstructed images. This process alternates between estimation and training until convergence. We evaluate the performance of our method across various imaging tasks, including inpainting, denoising, and deblurring. Experimental results demonstrate that our approach enables the learning of high-fidelity diffusion priors from noisy data, significantly enhancing reconstruction quality in imaging inverse problems.

Recent 3D Gaussian Splatting (3DGS) representations have demonstrated remarkable performance in novel view synthesis; further, material-lighting disentanglement on 3DGS warrants relighting capabilities and its adaptability to broader applications. While the general approach to the latter operation lies in integrating differentiable physically-based rendering (PBR) techniques to jointly recover BRDF materials and environment lighting, achieving a precise disentanglement remains an inherently difficult task due to the challenge of accurately modeling light transport. Existing approaches typically approximate Gaussian points' normals, which constitute an implicit geometric constraint. However, they usually suffer from inaccuracies in normal estimation that subsequently degrade light transport, resulting in noisy material decomposition and flawed relighting results. To address this, we propose GeoSplatting, a novel approach that augments 3DGS with explicit geometry guidance for precise light transport modeling. By differentiably constructing a surface-grounded 3DGS from an optimizable mesh, our approach leverages well-defined mesh normals and the opaque mesh surface, and additionally facilitates the use of mesh-based ray tracing techniques for efficient, occlusion-aware light transport calculations. This enhancement ensures precise material decomposition while preserving the efficiency and high-quality rendering capabilities of 3DGS. Comprehensive evaluations across diverse datasets demonstrate the effectiveness of GeoSplatting, highlighting its superior efficiency and state-of-the-art inverse rendering performance. The project page can be found at https://pku-vcl-geometry.github.io/GeoSplatting/.

We consider the problem of active 3D imaging using single-shot structured light systems, which are widely employed in commercial 3D sensing devices such as Apple Face ID and Intel RealSense. Traditional structured light methods typically decode depth correspondences through pixel-domain matching algorithms, resulting in limited robustness under challenging scenarios like occlusions, fine-structured details, and non-Lambertian surfaces. Inspired by recent advances in neural feature matching, we propose a learning-based structured light decoding framework that performs robust correspondence matching within feature space rather than the fragile pixel domain. Our method extracts neural features from the projected patterns and captured infrared (IR) images, explicitly incorporating their geometric priors by building cost volumes in feature space, achieving substantial performance improvements over pixel-domain decoding approaches. To further enhance depth quality, we introduce a depth refinement module that leverages strong priors from large-scale monocular depth estimation models, improving fine detail recovery and global structural coherence. To facilitate effective learning, we develop a physically-based structured light rendering pipeline, generating nearly one million synthetic pattern-image pairs with diverse objects and materials for indoor settings. Experiments demonstrate that our method, trained exclusively on synthetic data with multiple structured light patterns, generalizes well to real-world indoor environments, effectively processes various pattern types without retraining, and consistently outperforms both commercial structured light systems and passive stereo RGB-based depth estimation methods. Code and data are available at https://github.com/Namisntimpot/NSL

We show how to turn a noisy and fragile active triangulation technique-three-pattern structured light with a grayscale camera-into a fast and powerful tool for 3D capture: able to output sub-pixel accurate disparities at megapixel resolution, along with reflectance, normals, and a no-reference estimate of its own pixelwise 3D error. To achieve this, we formulate structured-light decoding as a neural inverse rendering problem. We show that despite having just three or four input images-all from the same viewpoint-this problem can be tractably solved by TurboSL, an algorithm that combines (1) a precise image formation model, (2) a signed distance field scene representation, and (3) projection Pattern sequences optimized for accuracy instead of precision. We use TurboSL to reconstruct a variety of complex scenes from images captured at up to 60 fps with a camera and a common projector. Our experiments highlight TurboSL's potential for dense and highly-accurate 3D acquisition from data captured in fractions of a second.

Diffusion models excel in solving imaging inverse problems due to their ability to model complex image priors. However, their reliance on large, clean datasets for training limits their practical use where clean data is scarce. In this paper, we propose EMDiffusion, an expectation-maximization (EM) approach to train diffusion models from corrupted observations. Our method alternates between reconstructing clean images from corrupted data using a known diffusion model (E-step) and refining diffusion model weights based on these reconstructions (M-step). This iterative process leads the learned diffusion model to gradually converge to a local optimum, that is, to approximate the true clean data distribution. We validate our method through extensive experiments on diverse computational imaging tasks, including random inpainting, denoising, and deblurring, achieving new state-of-the-art performance.

Recent years have witnessed the tremendous progress of 3D GANs for generating view-consistent radiance fields with photo-realism. Yet, high-quality generation of human radiance fields remains challenging, partially due to the limited human-related priors adopted in existing methods. We present HumanGen, a novel 3D human generation scheme with detailed geometry and 360° realistic free-view rendering. It explicitly marries the 3D human generation with various priors from the 2D generator and 3D reconstructor of humans through the design of “anchor image”. We introduce a hybrid feature representation using the anchor image to bridge the latent space of HumanGen with the existing 2D generator. We then adopt a pronged design to disentangle the generation of geometry and appearance. With the aid of the anchor image, we adapt a 3D reconstructor for fine-grained details synthesis and propose a two-stage blending scheme to boost appearance generation. Extensive experiments demonstrate our effectiveness for state-of-the-art 3D human generation regarding geometry details, texture quality, and free-view performance. Notably, HumanGen can also incorporate various off-the-shelf 2D latent editing methods, seamlessly lifting them into 3D.

Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion. Recent NeRF based methods achieve impressive fidelity of 3D reconstruction, but bake the lighting and shadows into the radiance field, while mesh-based methods that facilitate intrinsic decomposition through differentiable rendering have not yet scaled to the complexity and scale of outdoor scenes. We present a novel inverse rendering framework for large urban scenes capable of jointly reconstructing the scene geometry, spatially-varying materials, and HDR lighting from a set of posed RGB images with optional depth. Specifically, we use a neural field to account for the primary rays, and use an explicit mesh (reconstructed from the underlying neural field) for modeling secondary rays that produce higher-order lighting effects such as cast shadows. By faithfully disentangling complex geometry and materials from lighting effects, our method enables photorealistic relighting with specular and shadow effects on several outdoor datasets. Moreover, it supports physics-based scene manipulations such as virtual object insertion with ray-traced shadow casting.

Human modeling and relighting are two fundamental problems in computer vision and graphics, where high-quality datasets can largely facilitate related research. However, most existing human datasets only provide multi-view human images captured under the same illumination. Although valuable for modeling tasks, they are not read-ily used in relighting problems. To promote research in both fields, in this paper, we present UltraStage, a new 3D human dataset that contains more than 2, 000 high-quality human assets captured under both multi-view and multi-illumination settings. Specifically, for each example, we provide 32 surrounding views illuminated with one white light and two gradient illuminations. In addition to regular multi-view images, gradient illuminations help recover de-tailed surface normal and spatially-varying material maps, enabling various relighting applications. Inspired by recent advances in neural representation, we further interpret each example into a neural human asset which allows novel view synthesis under arbitrary lighting conditions. We show our neural human assets can achieve extremely high capture performance and are capable of representing fine details such as facial wrinkles and cloth folds. We also validate UltraStage in single image relighting tasks, training neural networks with virtual relighted data from neural assets and demonstrating realistic rendering improvements over prior arts. UltraStage will be publicly available to the community to stimulate significant future developments in various human modeling and rendering tasks. The dataset is available at https://miaoing.github.io/RNHA.

Autonomous vehicles (AV) require that neural networks used for perception be robust to different viewpoints if they are to be deployed across many types of vehicles without the repeated cost of data collection and labeling for each. AV companies typically focus on collecting data from diverse scenarios and locations, but not camera rig configurations, due to cost. As a result, only a small number of rig variations exist across most fleets. In this paper, we study how AV perception models are affected by changes in camera viewpoint and propose a way to scale them across vehicle types without repeated data collection and labeling. Using bird’s eye view (BEV) segmentation as a motivating task, we find through extensive experiments that existing perception models are surprisingly sensitive to changes in camera viewpoint. When trained with data from one camera rig, small changes to pitch, yaw, depth, or height of the camera at inference time lead to large drops in performance. We introduce a technique for novel view synthesis and use it to transform collected data to the viewpoint of target rigs, allowing us to train BEV segmentation models for diverse target rigs without any additional data collection or labeling cost. To analyze the impact of viewpoint changes, we leverage synthetic data to mitigate other gaps (content, ISP, etc). Our approach is then trained on real data and evaluated on synthetic data, enabling evaluation on diverse target rigs. We release all data for use in future work. Our method is able to recover an average of 14.7% of the IoU that is otherwise lost when deploying to new rigs.

Visual codes such as QR codes provide a low-cost and convenient communication channel between physical objects and mobile devices, but typically operate when the code and the device are in close physical proximity. We propose a system, called QfaR, which enables mobile devices to scan visual codes across long distances even where the image resolution of the visual codes is extremely low. QfaR is based on location-guided code scanning, where we utilize a crowd-sourced database of physical locations of codes. Our key observation is that if the approximate location of the codes and the user is known, the space of possible codes can be dramatically pruned down. Then, even if every "single bit" from the low-resolution code cannot be recovered, QfaR can still identify the visual code from the pruned list with high probability. By applying computer vision techniques, QfaR is also robust against challenging imaging conditions, such as tilt, motion blur, etc. Experimental results with common iOS and Android devices show that QfaR can significantly enhance distances at which codes can be scanned, e.g., 3.6cm-sized codes can be scanned at a distance of 7.5 meters, and 0.5m-sized codes at about 100 meters. QfaR has many potential applications, and beyond our diverse experiments, we also conduct a simple case study on its use for efficiently scanning QR code-based badges to estimate event attendance.

This work considers gradient-based mesh optimization, where we iteratively optimize for a 3D surface mesh by representing it as the isosurface of a scalar field, an increasingly common paradigm in applications including photogrammetry, generative modeling, and inverse physics. Existing implementations adapt classic isosurface extraction algorithms like Marching Cubes or Dual Contouring; these techniques were designed to extract meshes from fixed, known fields, and in the optimization setting they lack the degrees of freedom to represent high-quality feature-preserving meshes, or suffer from numerical instabilities. We introduce FlexiCubes, an isosurface representation specifically designed for optimizing an unknown mesh with respect to geometric, visual, or even physical objectives. Our main insight is to introduce additional carefully-chosen parameters into the representation, which allow local flexible adjustments to the extracted mesh geometry and connectivity. These parameters are updated along with the underlying scalar field via automatic differentiation when optimizing for a downstream task. We base our extraction scheme on Dual Marching Cubes for improved topological properties, and present extensions to optionally generate tetrahedral and hierarchically-adaptive meshes. Extensive experiments validate FlexiCubes on both synthetic benchmarks and real-world applications, showing that it offers significant improvements in mesh quality and geometric fidelity.

We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations. Unlike recent multi-view reconstruction approaches, which typically produce entangled 3D representations encoded in neural networks, we output triangle meshes with spatially-varying materials and environment lighting that can be deployed in any traditional graphics engine unmodified. We leverage recent work in differentiable rendering, coordinate-based networks to compactly represent volumetric texturing, alongside differentiable marching tetrahedrons to enable gradient-based optimization directly on the surface mesh. Finally, we introduce a differentiable formulation of the split sum approximation of environment lighting to efficiently recover all-frequency lighting. Experiments show our extracted models used in advanced scene editing, material decomposition, and high quality view interpolation, all running at interactive rates in triangle-based renderers (rasterizers and path tracers).

As several industries are moving towards modeling massive 3D virtual worlds, the need for content creation tools that can scale in terms of the quantity, quality, and diversity of 3D content is becoming evident. In our work, we aim to train performant 3D generative models that synthesize textured meshes which can be directly consumed by 3D rendering engines, thus immediately usable in downstream applications. Prior works on 3D generative modeling either lack geometric details, are limited in the mesh topology they can produce, typically do not support textures, or utilize neural renderers in the synthesis process, which makes their use in common 3D software non-trivial. In this work, we introduce GET3D, a Generative model that directly generates Explicit Textured 3D meshes with complex topology, rich geometric details, and high fidelity textures. We bridge recent success in the differentiable surface modeling, differentiable rendering as well as 2D Generative Adversarial Networks to train our model from 2D image collections. GET3D is able to generate high-quality 3D textured meshes, ranging from cars, chairs, animals, motorbikes and human characters to buildings, achieving significant improvements over previous methods.

We consider the challenging problem of predicting intrinsic object properties from a single image by exploiting differentiable renderers. Many previous learning-based approaches for inverse graphics adopt rasterization-based renderers and assume naive lighting and material models, which often fail to account for non-Lambertian, specular reflections commonly observed in the wild. In this work, we propose DIBR++, a hybrid differentiable renderer which supports these photorealistic effects by combining rasterization and ray-tracing, taking the advantage of their respective strengths---speed and realism. Our renderer incorporates environmental lighting and spatially-varying material models to efficiently approximate light transport, either through direct estimation or via spherical basis functions. Compared to more advanced physics-based differentiable renderers leveraging path tracing, DIBR++ is highly performant due to its compact and expressive shading model, which enables easy integration with learning frameworks for geometry, reflectance and lighting prediction from a single image without requiring any ground-truth. We experimentally demonstrate that our approach achieves superior material and lighting disentanglement on synthetic and real data compared to existing rasterization-based approaches and showcase several artistic applications including material editing and relighting.

We consider the problem of optimizing the performance of an active imaging system by automatically discovering the illuminations it should use, and the way to decode them. Our approach tackles two seemingly incompatible goals: (1) ''tuning'' the illuminations and decoding algorithm precisely to the devices at hand---to their optical transfer functions, non-linearities, spectral responses, image processing pipelines---and (2) doing so without modeling or calibrating the system; without modeling the scenes of interest; and without prior training data. The key idea is to formulate a stochastic gradient descent (SGD) optimization procedure that puts the actual system in the loop: projecting patterns, capturing images, and calculating the gradient of expected reconstruction error. We apply this idea to structured-light triangulation to ''auto-tune'' several devices---from smartphones and laser projectors to advanced computational cameras. Our experiments show that despite being model-free and automatic, optical SGD can boost system 3D accuracy substantially over state-of-the-art coding schemes.

With the advent of smart homes, smart cities, and smart everything, the Internet of Things (IoT) has emerged as an area of incredible impact, potential, and growth. Internet of Things date security remain a major challenge, in the current Internet of Things systems, a relatively easy method of data encryption is used to ensure the security of data transmission, which is commonly called lightweight cryptography. However, such method is at the risk of being cracked by quantum computers, which will contribute to many challenges specially related to privacy and security in IoT. As a result, the architecture of IoT needs to be re-designed considering the security challenges brought by quantum computers. On the other hand, Quantum Key Distribution (QKD) allows two users to share unconditionally secure keys. Unlike classical cryptosystems, the security of QKD is based on the fundamentals of quantum mechanics. This security of QKD is independent of computational complexity and will not be affected, no matter how much computing power the adversary has. This paper introduces a quantum key distribution enhanced Internet of Things architecture and proposes a residual-adaptive key provisioning scheme, which is evaluated in terms of key distribution success rate in the simulation.

Free-space long-distance quantum key distribution (QKD) has the characteristics of low attenuation and wide coverage, which can overcome the limitation of transmission distance based on ground optical fiber QKD networks. Long-distance QKD requests can be relayed by quantum satellites to achieve intercontinental QKD. At present, there is only one quantum satellite in space, quantum satellite network with multiple quantum satellites is necessary to be deployed to cover the global. Thus, how to construct the quantum satellite network becomes a new challenge. In this paper, we propose a centralized and distributed collaborative scheme of quantum satellite network. Low-Earth-orbit (LEO) quantum satellites, as important relay satellites, will affect the performance of the global QKD network. Based on the above architecture, we analyze the influence of the structure of LEO quantum satellite constellation on the QKD performance. Simulation results show that the key relay performance of the constellation is related to the form of inter-satellite link. and the more the number of satellites is, the greater the successful probability of the key relay services will be.

3D shape representations that accommodate learning-based 3D reconstruction are an open problem in machine learning and computer graphics. Previous work on neural 3D reconstruction demonstrated benefits, but also limitations, of point cloud, voxel, surface mesh, and implicit function representations. We introduce \emph{Deformable Tetrahedral Meshes} (DefTet) as a particular parameterization that utilizes volumetric tetrahedral meshes for the reconstruction problem. Unlike existing volumetric approaches, DefTet optimizes for both vertex placement and occupancy, and is differentiable with respect to standard 3D reconstruction loss functions. It is thus simultaneously high-precision, volumetric, and amenable to learning-based neural architectures. We show that it can represent arbitrary, complex topology, is both memory and computationally efficient, and can produce high-fidelity reconstructions with a significantly smaller grid size than alternative volumetric approaches. The predicted surfaces are also inherently defined as tetrahedral meshes, thus do not require post-processing. We demonstrate that DefTetmatches or exceeds both the quality of the previous best approaches and the performance of the fastest ones. Our approach obtains high-quality tetrahedral meshes computed directly from noisy point clouds, and is the first to showcase high-quality 3D results using only a single image as input.

Objects obscured by occluders are considered lost in the images acquired by conventional camera systems, prohibiting both visualization and understanding of such hidden objects. Non-line-of-sight methods (NLOS) aim at recovering information about hidden scenes, which could help make medical imaging less invasive, improve the safety of autonomous vehicles, and potentially enable capturing unprecedented high-definition RGB-D data sets that include geometry beyond the directly visible parts. Recent NLOS methods have demonstrated scene recovery from time-resolved pulse-illuminated measurements encoding occluded objects as faint indirect reflections. Unfortunately, these systems are fundamentally limited by the quartic intensity fall-off for diffuse scenes. With laser illumination limited by eye-safety limits, recovery algorithms must tackle this challenge by incorporating scene priors. However, existing NLOS reconstruction algorithms do not facilitate learning scene priors. Even if they did, datasets that allow for such supervision do not exist, and successful encoder-decoder networks and generative adversarial networks fail for real-world NLOS data. In this work, we close this gap by learning hidden scene feature representations tailored to both reconstruction and recognition tasks such as classification or object detection, while still relying on physical models at the feature level. We overcome the lack of real training data with a generalizable architecture that can be trained in simulation. We learn the differentiable scene representation jointly with the reconstruction task using a differentiable transient renderer in the objective, and demonstrate that it generalizes to unseen classes and unseen real-world scenes , unlike existing encoder-decoder architectures and generative adversarial networks. The proposed method allows for end-to-end training for different NLOS tasks , such as image reconstruction, classification, and object detection, while being memory-efficient and running at real-time rates. We demonstrate hidden view synthesis, RGB-D reconstruction, classification, and object detection in the hidden scene in an end-to-end fashion.

Conventional intensity cameras recover objects in the direct line-of-sight of the camera, whereas occluded scene parts are considered lost in this process. Non-line-of-sight imaging (NLOS) aims at recovering these occluded objects by analyzing their indirect reflections on visible scene surfaces. Existing NLOS methods temporally probe the indirect light transport to unmix light paths based on their travel time, which mandates specialized instrumentation that suffers from low photon efficiency, high cost, and mechanical scanning. We depart from temporal probing and demonstrate steady-state NLOS imaging using conventional intensity sensors and continuous illumination. Instead of assuming perfectly isotropic scattering, the proposed method exploits directionality in the hidden surface reflectance, resulting in (small) spatial variation of their indirect reflections for varying illumination. To tackle the shape-dependence of these variations, we propose a trainable architecture which learns to map diffuse indirect reflections to scene reflectance using only synthetic training data. Relying on consumer color image sensors, with high fill factor, high quantum efficiency and low read-out noise, we demonstrate high-fidelity color NLOS imaging for scene configurations tackled before with picosecond time resolution.

Manually labeling objects by tracing their boundaries is a laborious process. In Polygon-RNN++, the authors proposed Polygon-RNN that produces polygonal annotations in a recurrent manner using a CNN-RNN architecture, allowing interactive correction via humans-in-the-loop. We propose a new framework that alleviates the sequential nature of Polygon-RNN, by predicting all vertices simultaneously using a Graph Convolutional Network (GCN). Our model is trained end-to-end, and runs in real time. It supports object annotation by either polygons or splines, facilitating labeling efficiency for both line-based and curved objects. We show that Curve-GCN outperforms all existing approaches in automatic mode, including the powerful DeepLab, and is significantly more efficient in interactive mode than Polygon-RNN++. Our model runs at 29.3ms in automatic, and 2.6ms in interactive mode, making it 10x and 100x faster than Polygon-RNN++.

Many machine learning models operate on images, but ignore the fact that images are 2D projections formed by 3D geometry interacting with light, in a process called rendering. Enabling ML models to understand image formation might be key for generalization. However, due to an essential rasterization step involving discrete assignment operations, rendering pipelines are non-differentiable and thus largely inaccessible to gradient-based ML techniques. In this paper, we present DIB-Render, a novel rendering framework through which gradients can be analytically computed. Key to our approach is to view rasterization as a weighted interpolation, allowing image gradients to back-propagate through various standard vertex shaders within a single framework. Our approach supports optimizing over vertex positions, colors, normals, light directions and texture coordinates, and allows us to incorporate various well-known lighting models from graphics. We showcase our approach in two ML applications: single-image 3D object prediction, and 3D textured object generation, both trained using exclusively 2D supervision.

We consider the problem of automatically generating sequences of structured-light patterns for active stereo triangulation of a static scene. Unlike existing approaches that use predetermined patterns and reconstruction algorithms tied to them, we generate patterns on the fly in response to generic specifications: number of patterns, projector-camera arrangement, workspace constraints, spatial frequency content, etc. Our pattern sequences are specifically optimized to minimize the expected rate of correspondence errors under those specifications for an unknown scene, and are coupled to a sequence-independent algorithm for perpixel disparity estimation. To achieve this, we derive an objective function that is easy to optimize and follows from first principles within a maximum-likelihood framework. By minimizing it, we demonstrate automatic discovery of pattern sequences, in under three minutes on a laptop, that can outperform state-of-the-art triangulation techniques.

Understanding semantic similarity among images is the core of a wide range of computer graphics and computer vision applications. However, the visual context of images is often ambiguous as images that can be perceived with emphasis on different attributes. In this paper, we present a method for learning the semantic visual similarity among images, inferring their latent attributes and embedding them into multi-spaces corresponding to each latent attribute. We consider the multi-embedding problem as an optimization function that evaluates the embedded distances with respect to qualitative crowdsourced clusterings. The key idea of our approach is to collect and embed qualitative pairwise tuples that share the same attributes in clusters. To ensure similarity attribute sharing among multiple measures, image classification clusters are presented to, and solved by users. The collected image clusters are then converted into groups of tuples, which are fed into our group optimization algorithm that jointly infers the attribute similarity and multi-attribute embedding. Our multi-attribute embedding allows retrieving similar objects in different attribute spaces. Experimental results show that our approach outperforms state-of-the-art multi-embedding approaches on various datasets, and demonstrate the usage of the multi-attribute embedding in image retrieval application.

Human 3D pose estimation from a single image is a challenging task with numerous applications. Convolutional Neural Networks (CNNs) have recently achieved superior performance on the task of 2D pose estimation from a single image, by training on images with 2D annotations collected by crowd sourcing. This suggests that similar success could be achieved for direct estimation of 3D poses. However, 3D poses are much harder to annotate, and the lack of suitable annotated training images hinders attempts towards end-to-end solutions. To address this issue, we opt to automatically synthesize training images with ground truth pose annotations. Our work is a systematic study along this road. We find that pose space coverage and texture diversity are the key ingredients for the effectiveness of synthetic training data. We present a fully automatic, scalable approach that samples the human pose space for guiding the synthesis procedure and extracts clothing textures from real images. Furthermore, we explore domain adaptation for bridging the gap between our synthetic training images and real testing photos. We demonstrate that CNNs trained with our synthetic images out-perform those trained with real photos on 3D pose estimation tasks.

Abstract We introduce a novel method for enabling stereoscopic viewing of a scene from a single pre‐segmented image. Rather than attempting full 3D reconstruction or accurate depth map recovery, we hallucinate a rough approximation of the scene's 3D model using a number of simple depth and occlusion cues and shape priors. We begin by depth‐sorting the segments, each of which is assumed to represent a separate object in the scene, resulting in a collection of depth layers. The shapes and textures of the partially occluded segments are then completed using symmetry and convexity priors. Next, each completed segment is converted to a union of generalized cylinders yielding a rough 3D model for each object. Finally, the object depths are refined using an iterative ground fitting process. The hallucinated 3D model of the scene may then be used to generate a stereoscopic image pair, or to produce images from novel viewpoints within a small neighborhood of the original view. Despite the simplicity of our approach, we show that it compares favorably with state‐of‐the‐art depth ordering methods. A user study was conducted showing that our method produces more convincing stereoscopic images than existing semi‐interactive and automatic single image depth recovery methods.