We introduce Motion2VecSets, a 4D diffusion model for dynamic surface mesh generation from various ambiguous observations, including a sequence of RGB images, sparse and partial point clouds, and low-resolution voxel grids. While recent methods using neural field representations have shown success in modeling non-rigid objects, conventional feed-forward architectures struggle with noisy, partial, or sparse observations due to their deterministic nature. To address the inherent one-to-many mapping problem, we introduce a diffusion model that explicitly learns the shape and motion distribution of non-rigid objects through an iterative denoising process of compressed latent representations. The diffusion-based priors provide more plausible and diverse reconstructions under ambiguous conditions. Instead of relying on global latent codes, we represent 4D dynamics using latent sets. This novel 4D representation captures local shape and deformation patterns, leading to more accurate non-linear motion capture and significantly improving generalization capacity to unseen motions and identities. For temporally coherent tracking, we jointly denoise latent sets across frames and enable cross-frame information exchange. To reduce computational cost, we design an interleaved spatial-temporal attention block that alternately aggregates deformation latents along spatial and temporal dimensions. Extensive experiments on datasets of humans, animals, and articulated objects demonstrate that Motion2VecSets outperforms prior methods in reconstructing and tracking non-rigid deformations from various imperfect observations.

Current advances in human head modeling allow to generate plausible-looking 3D head models via neural representations, such as NeRFs and SDFs. Nevertheless, constructing complete high-fidelity head models with explicitly controlled animation remains an issue. Furthermore, completing the head geometry based on a partial observation, e.g. coming from a depth sensor, while preserving a high level of detail is often problematic for the existing methods. We introduce a generative model for detailed 3D head meshes on top of an articulated 3DMM which allows explicit animation and high-detail preservation at the same time. Our method is trained in two stages. First, we register a parametric head model with vertex displacements to each mesh of the recently introduced NPHM dataset of accurate 3D head scans. The estimated displacements are baked into a hand-crafted UV layout. Second, we train a StyleGAN model in order to generalize over the UV maps of displacements, which we later refer to HeadCraft. The decomposition of the parametric model and high-quality vertex displacements allows us to animate the model and modify the regions semantically. We demonstrate the results of unconditional sampling, fitting to a scan and editing. The code and data are available at https://seva100.github.io/headcraft.

We propose a training-free approach to 3D editing that enables the editing of a single shape within a few minutes. The edited 3D mesh aligns well with the prompts, and remains identical for regions that are not intended to be altered. To this end, we first project the 3D object onto 4-view images and perform synchronized multi-view image editing along with user-guided text prompts and user-provided rough masks. However, the targeted regions to be edited are ambiguous due to projection from 3D to 2D. To ensure precise editing only in intended regions, we develop a 3D segmentation pipeline that detects edited areas in 3D space, followed by a merging algorithm to seamlessly integrate edited 3D regions with the original input. Extensive experiments demonstrate the superiority of our method over previous approaches, enabling fast, high-quality editing while preserving unintended regions.

We present LT3SD, a novel latent diffusion model for large-scale 3D scene generation. Recent advances in diffusion models have shown impressive results in 3D object generation, but are limited in spatial extent and quality when extended to 3D scenes. To generate complex and diverse 3D scene structures, we introduce a latent tree representation to effectively encode both lower-frequency geometry and higher-frequency detail in a coarse-to-fine hierarchy. We can then learn a generative diffusion process in this latent 3D scene space, modeling the latent components of a scene at each resolution level. To synthesize large-scale scenes with varying sizes, we train our diffusion model on scene patches and synthesize arbitrary-sized output 3D scenes through shared diffusion generation across multiple scene patches. Through extensive experiments, we demonstrate the efficacy and benefits of LT3SD for large-scale, high-quality unconditional 3D scene generation and for probabilistic completion for partial scene observations.

We propose a novel approach for reconstructing animatable 3D Gaussian avatars from monocular videos captured by commodity devices like smartphones. Photorealistic 3D head avatar reconstruction from such recordings is challenging due to limited observations, which leaves unobserved regions under-constrained and can lead to artifacts in novel views. To address this problem, we introduce a multi-view head diffusion model, leveraging its priors to fill in missing regions and ensure view consistency in Gaussian splatting renderings. To enable precise viewpoint control, we use normal maps rendered from FLAME-based head reconstruction, which provides pixel-aligned inductive biases. We also condition the diffusion model on VAE features extracted from the input image to preserve facial identity and appearance details. For Gaussian avatar reconstruction, we distill multi-view diffusion priors by using iteratively denoised images as pseudo-ground truths, effectively mitigating over-saturation issues. To further improve photorealism, we apply latent upsampling priors to refine the denoised latent before decoding it into an image. We evaluate our method on the NeRSemble dataset, showing that GAF outperforms previous state-of-the-art methods in novel view synthesis. Furthermore, we demonstrate higher-fidelity avatar reconstructions from monocular videos captured on commodity devices. Project Page: https://tangjiapeng.github.io/projects/GAF

One practical approach to infer 3D scene structure from a single image is to retrieve a closely matching 3D model from a database and align it with the object in the image. Existing methods rely on supervised training with images and pose annotations, which limits them to a narrow set of object categories. To address this, we propose a weakly supervised 9-DoF alignment method for inexact 3D models that requires no pose annotations and generalizes to unseen categories. Our approach derives a novel feature space based on foundation features that ensure multi-view consistency and overcome symmetry ambiguities inherent in foundation features using a self-supervised triplet loss. Additionally, we introduce a texture-invariant pose refinement technique that performs dense alignment in normalized object coordinates, estimated through the enhanced feature space. We conduct extensive evaluations on the real-world ScanNet25k dataset, where our method outperforms SOTA weakly supervised baselines by +4.3% mean alignment accuracy and is the only weakly supervised approach to surpass the supervised ROCA by +2.7%. To assess generalization, we introduce SUN2CAD, a real-world test set with 20 novel object categories, where our method achieves SOTA results without prior training on them.

We present 3DGS-LM, a new method that accelerates the reconstruction of 3D Gaussian Splatting (3DGS) by replacing its ADAM optimizer with a tailored Levenberg-Marquardt (LM). Existing methods reduce the optimization time by decreasing the number of Gaussians or by improving the implementation of the differentiable rasterizer. However, they still rely on the ADAM optimizer to fit Gaussian parameters of a scene in thousands of iterations, which can take up to an hour. To this end, we change the optimizer to LM that runs in conjunction with the 3DGS differentiable rasterizer. For efficient GPU parallization, we propose a caching data structure for intermediate gradients that allows us to efficiently calculate Jacobian-vector products in custom CUDA kernels. In every LM iteration, we calculate update directions from multiple image subsets using these kernels and combine them in a weighted mean. Overall, our method is 20% faster than the original 3DGS while obtaining the same reconstruction quality. Our optimization is also agnostic to other methods that acclerate 3DGS, thus enabling even faster speedups compared to vanilla 3DGS.

Traditionally, creating photo-realistic 3D head avatars requires a studio-level multi-view capture setup and expensive optimization during test-time, limiting the use of digital human doubles to the VFX industry or offline renderings. To address this shortcoming, we present Avat3r, which regresses a high-quality and animatable 3D head avatar from just a few input images, vastly reducing compute requirements during inference. More specifically, we make Large Reconstruction Models animatable and learn a powerful prior over 3D human heads from a large multi-view video dataset. For better 3D head reconstructions, we employ position maps from DUSt3R and generalized feature maps from the human foundation model Sapiens. To animate the 3D head, our key discovery is that simple cross-attention to an expression code is already sufficient. Finally, we increase robustness by feeding input images with different expressions to our model during training, enabling the reconstruction of 3D head avatars from inconsistent inputs, e.g., an imperfect phone capture with accidental movement, or frames from a monocular video. We compare Avat3r with current state-of-the-art methods for few-input and single-input scenarios, and find that our method has a competitive advantage in both tasks. Finally, we demonstrate the wide applicability of our proposed model, creating 3D head avatars from images of different sources, smartphone captures, single images, and even out-of-domain inputs like antique busts. Project website: https://tobias-kirschstein.github.io/avat3r/

We introduce MeshPad, a generative approach that creates 3D meshes from sketch inputs. Building on recent advances in artist-reminiscent triangle mesh generation, our approach addresses the need for interactive mesh creation. To this end, we focus on enabling consistent edits by decomposing editing into 'deletion' of regions of a mesh, followed by 'addition' of new mesh geometry. Both operations are invoked by simple user edits of a sketch image, facilitating an iterative content creation process and enabling the construction of complex 3D meshes. Our approach is based on a triangle sequence-based mesh representation, exploiting a large Transformer model for mesh triangle addition and deletion. In order to perform edits interactively, we introduce a vertex-aligned speculative prediction strategy on top of our additive mesh generator. This speculator predicts multiple output tokens corresponding to a vertex, thus significantly reducing the computational cost of inference and accelerating the editing process, making it possible to execute each editing step in only a few seconds. Comprehensive experiments demonstrate that MeshPad outperforms state-of-the-art sketch-conditioned mesh generation methods, achieving more than 22% mesh quality improvement in Chamfer distance, and being preferred by 90% of participants in perceptual evaluations.

Surface reconstruction is fundamental to computer vision and graphics, enabling applications in 3D modeling, mixed reality, robotics, and more. Existing approaches based on volumetric rendering obtain promising results, but optimize on a per-scene basis, resulting in a slow optimization that can struggle to model under-observed or textureless regions. We introduce QuickSplat, which learns data-driven priors to generate dense initializations for 2D gaussian splatting optimization of large-scale indoor scenes. This provides a strong starting point for the reconstruction, which accelerates the convergence of the optimization and improves the geometry of flat wall structures. We further learn to jointly estimate the densification and update of the scene parameters during each iteration; our proposed densifier network predicts new Gaussians based on the rendering gradients of existing ones, removing the needs of heuristics for densification. Extensive experiments on large-scale indoor scene reconstruction demonstrate the superiority of our data-driven optimization. Concretely, we accelerate runtime by 8x, while decreasing depth errors by up to 48% in comparison to state of the art methods.

Accurate, real-time 3D reconstruction of human heads from monocular images and videos underlies numerous visual applications. As 3D ground truth data is hard to come by at scale, previous methods have sought to learn from abundant 2D videos in a self-supervised manner. Typically, this involves the use of differentiable mesh rendering, which is effective but faces limitations. To improve on this, we propose SHeaP (Self-supervised Head Geometry Predictor Learned via 2D Gaussians). Given a source image, we predict a 3DMM mesh and a set of Gaussians that are rigged to this mesh. We then reanimate this rigged head avatar to match a target frame, and backpropagate photometric losses to both the 3DMM and Gaussian prediction networks. We find that using Gaussians for rendering substantially improves the effectiveness of this self-supervised approach. Training solely on 2D data, our method surpasses existing self-supervised approaches in geometric evaluations on the NoW benchmark for neutral faces and a new benchmark for non-neutral expressions. Our method also produces highly expressive meshes, outperforming state-of-the-art in emotion classification.

We present PBR-SR, a novel method for physically based rendering (PBR) texture super resolution (SR). It outputs high-resolution, high-quality PBR textures from low-resolution (LR) PBR input in a zero-shot manner. PBR-SR leverages an off-the-shelf super-resolution model trained on natural images, and iteratively minimizes the deviations between super-resolution priors and differentiable renderings. These enhancements are then back-projected into the PBR map space in a differentiable manner to produce refined, high-resolution textures. To mitigate the effects of view inconsistency and lighting sensitivity inherent to view-based super-resolution, our approach incorporates 2D prior constraints across multi-view renderings, enabling iterative refinement of shared upscaled textures. In parallel, we incorporate identity constraints directly in the PBR texture domain to ensure the upscaled textures remain faithful to the LR input. PBR-SR operates without any additional training or data requirements, relying entirely on pretrained image priors. We demonstrate that our approach produces high-fidelity PBR textures for both artist-designed and AI-generated meshes, outperforming both direct SR models application and prior texture optimization methods. Our results show high-quality outputs in both PBR and rendering evaluations, supporting advanced applications such as relighting.

We propose LiteReality, a novel pipeline that converts RGB-D scans of indoor environments into compact, realistic, and interactive 3D virtual replicas. LiteReality not only reconstructs scenes that visually resemble reality but also supports key features essential for graphics pipelines—such as object individuality, articulation, high-quality physically based rendering materials. At its core, LiteReality first performs scene understanding and parses the results into a coherent 3D layout and objects, with the help of a structured scene graph. It then reconstructs the scene by retrieving the most visually similar 3D artist-crafted models from a curated asset database. Later, the Material Painting module enhances the realism of retrieved objects by recovering high-quality, spatially varying materials. Finally, the reconstructed scene is integrated into a simulation engine with basic physical properties applied to enable interactive behavior. The resulting scenes are compact, editable, and fully compatible with standard graphics pipelines, making them suitable for applications in AR/VR, gaming, robotics, and digital twins. In addition, LiteReality introduces a training-free object retrieval module that achieves state-of-the-art similarity performance, as benchmarked on the Scan2CAD dataset, along with a robust Material Painting module capable of transferring appearances from images of any style to 3D assets—even in the presence of severe misalignment, occlusion, and poor lighting. We demonstrate the effectiveness of LiteReality on both real-life scans and public datasets.

We introduce IntrinsiX, a novel method that generates high-quality intrinsic images from text description. In contrast to existing text-to-image models whose outputs contain baked-in scene lighting, our approach predicts physically-based rendering (PBR) maps. This enables the generated outputs to be used for content creation scenarios in core graphics applications that facilitate re-lighting, editing, and texture generation tasks. In order to train our generator, we exploit strong image priors, and pre-train separate models for each PBR material component (albedo, roughness, metallic, normals). We then align these models with a new cross-intrinsic attention formulation that concatenates key and value features in a consistent fashion. This allows us to exchange information between each output modality and to obtain semantically coherent PBR predictions. To ground each intrinsic component, we propose a rendering loss which provides image-space signals to constrain the model, thus facilitating sharp details also in the output BRDF properties. Our results demonstrate detailed intrinsic generation with strong generalization capabilities that outperforms existing intrinsic image decomposition methods used with generated images by a significant margin. Finally, we show a series of applications, including re-lighting, editing, and for the first time text-conditioned room-scale PBR texture generation. We will release the code and the pre-trained model weights.

Volumetric rendering has become central to modern novel view synthesis methods, which use differentiable rendering to optimize 3D scene representations directly from observed views. While many recent works build on NeRF or 3D Gaussians, we explore an alternative volumetric scene representation. More specifically, we introduce two new scene representations based on linear primitives - octahedra and tetrahedra - both of which define homogeneous volumes bounded by triangular faces. To optimize these primitives, we present a differentiable rasterizer that runs efficiently on GPUs, allowing end-to-end gradient-based optimization while maintaining real-time rendering capabilities. Through experiments on real-world datasets, we demonstrate comparable performance to state-of-the-art volumetric methods while requiring fewer primitives to achieve similar reconstruction fidelity. Our findings deepen the understanding of 3D representations by providing insights into the fidelity and performance characteristics of transparent polyhedra and suggest that adopting novel primitives can expand the available design space.

We introduce *BecomingLit*, a novel method for reconstructing relightable, high-resolution head avatars that can be rendered from novel viewpoints at interactive rates. Therefore, we propose a new low-cost light stage capture setup, tailored specifically towards capturing faces. Using this setup, we collect a novel dataset consisting of diverse multi-view sequences of numerous subjects under varying illumination conditions and facial expressions. By leveraging our new dataset, we introduce a new relightable avatar representation based on 3D Gaussian primitives that we animate with a parametric head model and an expression-dependent dynamics module. We propose a new hybrid neural shading approach, combining a neural diffuse BRDF with an analytical specular term. Our method reconstructs disentangled materials from our dynamic light stage recordings and enables all-frequency relighting of our avatars with both point lights and environment maps. In addition, our avatars can easily be animated and controlled from monocular videos. We validate our approach in extensive experiments on our dataset, where we consistently outperform existing state-of-the-art methods in relighting and reenactment by a significant margin.

We introduce ROGR, a novel approach that reconstructs a relightable 3D model of an object captured from multiple views, driven by a generative relighting model that simulates the effects of placing the object under novel environment illuminations. Our method samples the appearance of the object under multiple lighting environments, creating a dataset that is used to train a lighting-conditioned Neural Radiance Field (NeRF) that outputs the object's appearance under any input environmental lighting. The lighting-conditioned NeRF uses a novel dual-branch architecture to encode the general lighting effects and specularities separately. The optimized lighting-conditioned NeRF enables efficient feed-forward relighting under arbitrary environment maps without requiring per-illumination optimization or light transport simulation. We evaluate our approach on the established TensoIR and Stanford-ORB datasets, where it improves upon the state-of-the-art on most metrics, and showcase our approach on real-world object captures.

Generating 3D worlds from text is a highly anticipated goal in computer vision. Existing works are limited by the degree of exploration they allow inside of a scene, i.e., produce streched-out and noisy artifacts when moving beyond central or panoramic perspectives. To this end, we propose WorldExplorer, a novel method based on autoregressive video trajectory generation, which builds fully navigable 3D scenes with consistent visual quality across a wide range of viewpoints. We initialize our scenes by creating multi-view consistent images corresponding to a 360 degree panorama. Then, we expand it by leveraging video diffusion models in an iterative scene generation pipeline. Concretely, we generate multiple videos along short, pre-defined trajectories, that explore the scene in depth, including motion around objects. Our novel scene memory conditions each video on the most relevant prior views, while a collision-detection mechanism prevents degenerate results, like moving into objects. Finally, we fuse all generated views into a unified 3D representation via 3D Gaussian Splatting optimization. Compared to prior approaches, WorldExplorer produces high-quality scenes that remain stable under large camera motion, enabling for the first time realistic and unrestricted exploration. We believe this marks a significant step toward generating immersive and truly explorable virtual 3D environments.

We introduce LightIt, a method for explicit illumination control for image generation. Recent generative methods lack lighting control, which is crucial to numerous artis-tic aspects of image generation such as setting the overall mood or cinematic appearance. To overcome these limi-tations, we propose to condition the generation on shading and normal maps. We model the lighting with single bounce shading, which includes cast shadows. We first train a shading estimation module to generate a dataset of real-world images and shading pairs. Then, we train a control network using the estimated shading and normals as input. Our method demonstrates high-quality image generation and lighting control in numerous scenes. Additionally, we use our generated dataset to train an identity-preserving re-lighting model, conditioned on an image and a target shading. Our method is the first that enables the generation of images with controllable, consistent lighting and performs on par with specialized relighting state-of-the-art methods.

We present Intrinsic Image Diffusion, a generative model for appearance decomposition of indoor scenes. Given a single input view, we sample multiple possible material ex-planations represented as albedo, roughness, and metal-lic maps. Appearance decomposition poses a considerable challenge in computer vision due to the inherent ambigu-ity between lighting and material properties and the lack of real datasets. To address this issue, we advocate for a probabilistic formulation, where instead of attempting to directly predict the true material properties, we employ a conditional generative model to sample from the solution space. Furthermore, we show that utilizing the strong learned prior of recent diffusion models trained on large-scale real-world images can be adapted to material estimation and highly improves the generalization to real images. Our method produces significantly sharper, more consis-tent, and more detailed materials, outperforming state-of-the-art methods by 1.5dB on PSNR and by 45% better FID score on albedo prediction. We demonstrate the effective-ness of our approach through experiments on both synthetic and real-world datasets.

We introduce FaceTalk11Project Page: https://shivangi-aneja.github.io/projects/facetalk, a novel generative approach designed for synthesizing high-fidelity 3D motion sequences of talking human heads from input audio signal. To capture the expressive, detailed nature of human heads, including hair, ears, and finer-scale eye movements, we propose to couple speech signal with the latent space of neural parametric head models to create high-fidelity, temporally coherent motion sequences. We propose a new latent diffusion model for this task, operating in the expression space of neural parametric head models, to synthesize audio-driven realistic head sequences. In the absence of a dataset with corresponding NPHM expressions to audio, we optimize for these correspondences to produce a dataset of temporally-optimized NPHM expressions fit to audio-video recordings of people talking. To the best of our knowledge, this is the first work to propose a generative approach for realistic and high-quality motion synthesis of volumetric human heads, representing a significant advancement in the field of audio-driven 3D animation. Notably, our approach stands out in its ability to generate plausible motion sequences that can produce high-fidelity head animation coupled with the NPHM shape space. Our experimental results substantiate the effectiveness of FaceTalk, consistently achieving superior and visually natural motion, encompassing diverse facial expressions and styles, outperforming existing methods by 75% in perceptual user study evaluation.

We introduce Motion2VecSets, a 4D diffusion model for dynamic surface reconstruction from point cloud sequences. While existing state-of-the-art methods have demonstrated success in reconstructing non-rigid objects using neural field representations, conventional feed-forward networks encounter challenges with ambiguous observations from noisy, partial, or sparse point clouds. To address these challenges, we introduce a diffusion model that explicitly learns the shape and motion distribution of non-rigid objects through an iterative denoising process of compressed latent representations. The diffusion-based priors enable more plausible and probabilistic reconstructions when handling ambiguous inputs. We parameterize 4D dynamics with latent sets instead of using global latent codes. This novel 4D representation allows us to learn local shape and deformation patterns, leading to more accurate nonlinear motion capture and significantly improving generalizability to unseen motions and identities. For more temporally-coherent object tracking, we synchronously denoise deformation latent sets and exchange information across multiple frames. To avoid computational overhead, we designed an interleaved space and time attention block to alternately aggregate deformation latents along spatial and temporal domains. Extensive comparisons against state-of-the-art methods demonstrate the superiority of our Motion2VecSets in 4D reconstruction from various imperfect observations.

We propose SceneTex, a novel method for effectively gen-erating high-quality and style-consistent textures for indoor scenes using depth-to-image diffusion priors. Unlike pre-vious methods that either iteratively warp 2D views onto a mesh surface or distillate diffusion latent features with-out accurate geometric and style cues, SceneTexformulates the texture synthesis task as an optimization problem in the RGB space where style and geometry consistency are prop-erly reflected. At its core, SceneTex proposes a multires-olution texture field to implicitly encode the mesh appear-ance. We optimize the target texture via a score-distillation-based objective function in respective RGB renderings. To further secure the style consistency across views, we introduce a cross-attention decoder to predict the RGB values by cross-attending to the pre-sampled reference locations in each instance. SceneTex enables various and accurate texture synthesis for 3D-FRONT scenes, demonstrating sig-nificant improvements in visual quality and prompt fidelity over the prior texture generation methods.

We present Monocular Neural Parametric Head Models (MonoNPHM) for dynamic 3D head reconstructions from monocular RGB videos. To this end, we propose a latent appearance space that parameterizes a texture field on top of a neural parametric model. We constrain predicted color values to be correlated with the underlying geometry such that gradients from RGB effectively influence latent geometry codes during inverse rendering. To increase the representational capacity of our expression space, we augment our backward deformation field with hyper-dimensions, thus improving color and geometry representation in topologically challenging expressions. Using MonoNPHM as a learned prior, we approach the task of 3D head reconstruction using signed distance field based volumetric rendering. By numerically inverting our backward deformation field, we incorporated a landmark loss using facial anchor points that are closely tied to our canonical geometry representation. To evaluate the task of dynamic face reconstruction from monocular RGB videos we record 20 challenging Kinect sequences under casual conditions. MonoNPHM outper-forms all baselines with a significant margin, and makes an important step towards easily accessible neural parametric face models through RGB tracking.

3D asset generation is getting massive amounts of attention, inspired by the recent success of text-guided 2D content creation. Existing text-to-3D methods use pretrained text-to-image diffusion models in an optimization problem or fine-tune them on synthetic data, which often results in non-photorealistic 3D objects without backgrounds. In this paper, we present a method that leverages pretrained text-to-image models as a prior, and learn to generate multi-view images in a single denoising process from real-world data. Concretely, we propose to integrate 3D volume-rendering and cross-frame-attention layers into each block of the existing U-Net network of the text-to-image model. Moreover, we design an autoregressive generation that renders more 3D-consistent images at any viewpoint. We train our model on real-world datasets of objects and showcase its capabilities to generate instances with a variety of high-quality shapes and textures in authentic surroundings. Compared to the existing methods, the results generated by our method are consistent, and have favorable visual quality (−30% FID, −37% KID).

DiffusionAvatars synthesizes a high-fidelity 3D head avatar of a person, offering intuitive control over both pose and expression. We propose a diffusion-based neural ren-derer that leverages generic 2D priors to produce com-pelling images of faces. For coarse guidance of the expression and head pose, we render a neural parametric head model (NPHM) from the target viewpoint, which acts as a proxy geometry of the person. Additionally, to enhance the modeling of intricate facial expressions, we condition DiffusionAvatars directly on the expression codes obtained from NPHM via cross-attention. Finally, to synthesize consistent surface details across different viewpoints and ex-pressions, we rig learnable spatial features to the head's surface via TriPlane lookup in NPHM's canonical space. We train DiffusionAvatars on RGB videos and corresponding fitted NPHM meshes of a person and test the obtained avatars in both self-reenactment and animation scenarios. Our experiments demonstrate that DiffusionAvatars gener-ates temporally consistent and visually appealing videos for novel poses and expressions of a person, outperforming ex-isting approaches.

We introduce MultiDiff, a novel approach for consistent novel view synthesis of scenes from a single RGB image. The task of synthesizing novel views from a single reference image is highly ill-posed by nature, as there exist multiple, plausible explanations for unobserved areas. To address this issue, we incorporate strong priors in form of monocular depth predictors and video-diffusion models. Monocular depth enables us to condition our model on warped reference images for the target views, increasing geometric stability. The video-diffusion prior provides a strong proxy for 3D scenes, allowing the model to learn continuous and pixel-accurate correspondences across generated images. In contrast to approaches relying on autoregressive image generation that are prone to drifts and error accumulation, MultiDiff Jointly synthesizes a sequence of frames yielding high-quality and multi-view consistent results - even for long-term scene generation with large camera movements, while reducing inference time by an order of magnitude. For additional consistency and image quality improvements, we introduce a novel, structured noise distribution. Our experimental results demonstrate that MultiDiff outperforms state-of-the-art methods on the challenging, real-world datasets RealEstate10K and ScanNet. Finally, our model naturally supports multi-view consistent editing without the need for further tuning.

We introduce GaussianAvatars11Project page: https://shenhanqian.github.io/gaussian-avatars, a new method to create photorealistic head avatars that are fully controllable in terms of expression, pose, and viewpoint. The core idea is a dynamic 3D representation based on 3D Gaussian splats that are rigged to a parametric morphable face model. This combination facilitates photorealistic rendering while allowing for precise animation control via the underlying parametric model, e.g., through expression transfer from a driving sequence or by manually changing the morphable model parameters. We parameterize each splat by a local coordinate frame of a triangle and optimize for explicit dis-placement offset to obtain a more accurate geometric representation. During avatar reconstruction, we jointly optimize for the morphable model parameters and Gaussian splat parameters in an end-to-end fashion. We demonstrate the animation capabilities of our photorealistic avatar in several challenging scenarios. For instance, we show reen-actments from a driving video, where our method outperforms existing works by a significant margin.

We introduce MeshGPT, a new approach for generating triangle meshes that reflects the compactness typical of artist-created meshes, in contrast to dense triangle meshes extracted by iso-surfacing methods from neural fields. Inspired by recent advances in powerful large language models, we adopt a sequence-based approach to autoregressively generate triangle meshes as sequences of triangles. We first learn a vocabulary of latent quantized embeddings, using graph convolutions, which inform these embeddings of the local mesh geometry and topology. These embeddings are sequenced and decoded into triangles by a decoder, ensuring that they can effectively reconstruct the mesh. A transformer is then trained on this learned vocabulary to predict the index of the next embedding given previous embeddings. Once trained, our model can be autoregressively sampled to generate new triangle meshes, directly generating compact meshes with sharp edges, more closely imitating the efficient triangulation patterns of human-crafted meshes. MeshGPT demonstrates a notable improvement over state of the art mesh generation methods, with a 9% increase in shape coverage and a 30-point enhancement in FID scores across various categories.

We introduce Diffusion Parametric Head Models (DPHMs), a generative model that enables robust volumetric head reconstruction and tracking from monocular depth sequences. While recent volumetric head models, such as NPHMs, can now excel in representing high-fidelity head geometries, tracking and reconstructing heads from real-world single-view depth sequences remains very challenging, as the fitting to partial and noisy observations is under-constrained. To tackle these challenges, we propose a latent diffusion-based prior to regularize volumetric head reconstruction and tracking. This prior-based regularizer effectively constrains the identity and expression codes to lie on the underlying latent manifold which represents plausible head shapes. To evaluate the effectiveness of the diffusion-based prior, we collect a dataset of monocular Kinect sequences consisting of various complex facial expression motions and rapid transitions. We compare our method to state-of-the-art tracking methods and demonstrate improved head identity reconstruction as well as robust expression tracking.

We present DiffuScene for indoor 3D scene synthesis based on a novel scene configuration denoising diffusion model. It generates 3D instance properties stored in an unordered object set and retrieves the most similar geometry for each object configuration, which is characterized as a concatenation of different attributes, including location, size, orientation, semantics, and geometry features. We introduce a diffusion network to synthesize a collection of 3D indoor objects by denoising a set of unordered object attributes. Unordered parametrization simplifies and eases the joint distribution approximation. The shape feature diffusion facilitates natural object placements, including symmetries. Our method enables many downstream applications, including scene completion, scene arrangement, and text-conditioned scene synthesis. Experiments on the 3D-FRONT dataset show that our method can synthesize more physically plausible and diverse indoor scenes than state-of-the-art methods. Extensive ablation studies verify the effectiveness of our design choice in scene diffusion models.

Recently, progress in acquisition equipment such as LiDAR sensors has enabled sensing increasingly spacious outdoor 3D environments. Making sense of such 3D acquisitions requires fine-grained scene understanding, such as constructing instance-based 3D scene segmentations. Commonly, a neural network is trained for this task; however, this requires access to a large, densely annotated dataset, which is widely known to be challenging to obtain. To address this issue, in this work we propose to predict instance segmentations for 3D scenes in an unsupervised way, without relying on ground-truth annotations. To this end, we construct a learning framework consisting of two components: (1) a pseudo-annotation scheme for generating initial unsupervised pseudo-labels; and (2) a self-training algorithm for instance segmentation to fit robust, accurate instances from initial noisy proposals. To enable generating 3D instance mask proposals, we construct a weighted proxy-graph by connecting 3D points with edges integrating multi-modal image-and point-based self-supervised features, and perform graphcuts to isolate individual pseudo-instances. We then build on a state-of-the-art point-based architecture and train a 3D instance segmentation model, resulting in significant refinement of initial proposals. To scale to arbitrary complexity 3D scenes, we design our algorithm to operate on local 3D point chunks and construct a merging step to generate scene-level instance segmentations. Experiments on the challenging SemanticKITTI benchmark demonstrate the potential of our approach, where it attains 13.3% higher Average Precision and 9.1% higher F1 score compared to the best-performing baseline. The code is publicly available at https://github.com/artonson/autoinst.

Recently, significant progress has been achieved in sensing real large-scale outdoor 3D environments, particularly by using modern acquisition equipment such as LiDAR sensors. Unfortunately, they are fundamentally limited in their ability to produce dense, complete 3D scenes. To address this issue, recent learning-based methods integrate neural implicit representations and optimizable feature grids to approximate surfaces of 3D scenes. However, naively fitting samples along raw LiDAR rays leads to noisy 3D mapping results due to the nature of sparse, conflicting LiDAR measurements. Instead, in this work we depart from fitting LiDAR data exactly, instead letting the network optimize a non-metric monotonic implicit field defined in 3D space. To fit our field, we design a learning system integrating a monotonicity loss that enables optimizing neural monotonic fields and leverages recent progress in large-scale 3D mapping. Our algorithm achieves high-quality dense 3D mapping performance as cap¬tured by multiple quantitative and perceptual measures and visual results obtained for Mai City, Newer College, and KITTI benchmarks. The code of our approach is publicly available at https://github.com/artonson/deepmif.

We present a novel diffusion-based approach for coherent 3D scene reconstruction from a single RGB image. Our method utilizes an image-conditioned 3D scene diffusion model to simultaneously denoise the 3D poses and geometries of all objects within the scene. Motivated by the ill-posed nature of the task and to obtain consistent scene reconstruction results, we learn a generative scene prior by conditioning on all scene objects simultaneously to capture scene context and by allowing the model to learn inter-object relationships throughout the diffusion process. We further propose an efficient surface alignment loss to facilitate training even in the absence of full ground-truth annotation, which is common in publicly available datasets. This loss leverages an expressive shape representation, which enables direct point sampling from intermediate shape predictions. By framing the task of single RGB image 3D scene reconstruction as a conditional diffusion process, our approach surpasses current state-of-the-art methods, achieving a 12.04\% improvement in AP3D on SUN RGB-D and a 13.43\% increase in F-Score on Pix3D.

Learning 3D head priors from large 2D image collections is an important step towards high-quality 3D-aware human modeling. A core requirement is an efficient architecture that scales well to large-scale datasets and large image resolutions. Unfortunately, existing 3D GANs struggle to scale to generate samples at high resolutions due to their relatively slow train and render speeds, and typically have to rely on 2D superresolution networks at the expense of global 3D consistency. To address these challenges, we propose Generative Gaussian Heads (GGHead), which adopts the recent 3D Gaussian Splatting representation within a 3D GAN framework. To generate a 3D representation, we employ a powerful 2D CNN generator to predict Gaussian attributes in the UV space of a template head mesh. This way, GGHead exploits the regularity of the template's UV layout, substantially facilitating the challenging task of predicting an unstructured set of 3D Gaussians. We further improve the geometric fidelity of the generated 3D representations with a novel total variation loss on rendered UV coordinates. Intuitively, this regularization encourages that neighboring rendered pixels should stem from neighboring Gaussians in the template's UV space. Taken together, our pipeline can efficiently generate 3D heads trained only from single-view 2D image observations. Our proposed framework matches the quality of existing 3D head GANs on FFHQ while being both substantially faster and fully 3D consistent. As a result, we demonstrate real-time generation and rendering of high-quality 3D-consistent heads at $1024^2$ resolution for the first time. Project Website: https://tobias-kirschstein.github.io/gghead

We propose L3DG, the first approach for generative 3D modeling of 3D Gaussians through a latent 3D Gaussian diffusion formulation. This enables effective generative 3D modeling, scaling to generation of entire room-scale scenes which can be very efficiently rendered. To enable effective synthesis of 3D Gaussians, we propose a latent diffusion formulation, operating in a compressed latent space of 3D Gaussians. This compressed latent space is learned by a vector-quantized variational autoencoder (VQ-VAE), for which we employ a sparse convolutional architecture to efficiently operate on room-scale scenes. This way, the complexity of the costly generation process via diffusion is substantially reduced, allowing higher detail on object-level generation, as well as scalability to large scenes. By leveraging the 3D Gaussian representation, the generated scenes can be rendered from arbitrary viewpoints in real-time. We demonstrate that our approach significantly improves visual quality over prior work on unconditional object-level radiance field synthesis and showcase its applicability to room-scale scene generation.

Recent progress in NeRF-based GANs has introduced a number of approaches for high-resolution and high-fidelity generative modeling of human heads with a possibility for novel view rendering. At the same time, one must solve an inverse problem to be able to re-render or modify an existing image or video. Despite the success of universal optimization-based methods for 2D GAN inversion, those applied to 3D GANs may fail to extrapolate the result onto the novel view, whereas optimization-based 3D GAN in-version methods are time-consuming and can require at least several minutes per image. Fast encoder-based techniques, such as those developed for StyleGAN, may also be less appealing due to the lack of identity preservation. Our work introduces a fast technique that bridges the gap between the two approaches by directly utilizing the tri-plane representation presented for the EG3D generative model. In particular, we build upon a feed-forward convolutional encoder for the latent code and extend it with a fully-convolutional predictor of tri-plane numerical offsets. The renderings are similar in quality to the ones produced by optimization-based techniques and outperform the ones by encoder-based methods. As we empirically prove, this is a consequence of directly operating in the tri-plane space, not in the GAN parameter space, while making use of an encoder-based trainable approach. Finally, we demonstrate significantly more correct embedding of a face image in 3D than for all the baselines, further strengthened by a probably symmetric prior enabled during training.

Abstract The field of visual computing is rapidly advancing due to the emergence of generative artificial intelligence (AI), which unlocks unprecedented capabilities for the generation, editing, and reconstruction of images, videos, and 3D scenes. In these domains, diffusion models are the generative AI architecture of choice. Within the last year alone, the literature on diffusion‐based tools and applications has seen exponential growth and relevant papers are published across the computer graphics, computer vision, and AI communities with new works appearing daily on arXiv. This rapid growth of the field makes it difficult to keep up with all recent developments. The goal of this state‐of‐the‐art report (STAR) is to introduce the basic mathematical concepts of diffusion models, implementation details and design choices of the popular Stable Diffusion model, as well as overview important aspects of these generative AI tools, including personalization, conditioning, inversion, among others. Moreover, we give a comprehensive overview of the rapidly growing literature on diffusion‐based generation and editing, categorized by the type of generated medium, including 2D images, videos, 3D objects, locomotion, and 4D scenes. Finally, we discuss available datasets, metrics, open challenges, and social implications. This STAR provides an intuitive starting point to explore this exciting topic for researchers, artists, and practitioners alike.

Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without using any 3D annotations. The key idea of our approach is to design a trainable model that employs both incomplete 3D reconstructions and their corresponding source RGB-D images, fusing cross-domain features into volumetric embeddings to predict complete 3D geometry, color, and semantics with only 2D labeling which can be either manual or machine-generated. Our key technical innovation is to leverage differentiable rendering of color and semantics to bridge 2D observations and unknown 3D space, using the observed RGB images and 2D semantics as supervision, respectively. We additionally develop a learning pipeline and corresponding method to enable learning from imperfect predicted 2D labels, which could be additionally acquired by synthesizing in an augmented set of virtual training views complementing the original real captures, enabling more efficient self-supervision loop for semantics. As a result, our end-to-end trainable solution jointly addresses geometry completion, colorization, and semantic mapping from limited RGB-D images, without relying on any 3D ground-truth information. Our method achieves state-of-the-art performance of semantic scene completion on two large-scale benchmark datasets MatterPort3D and ScanNet, surpasses baselines even with costly 3D annotations in predicting both geometry and semantics. To our knowledge, our method is also the first 2D-driven method addressing completion and semantic segmentation of real-world 3D scans simultaneously.

Despite the recent attention to DeepFakes, one of the most prevalent ways to mislead audiences on social media is the use of unaltered images in a new but false context. We propose a new method that automatically highlights out-of-context image and text pairs, for assisting fact-checkers. Our key insight is to leverage the grounding of images with text to distinguish out-of-context scenarios that cannot be disambiguated with language alone. We propose a self-supervised training strategy where we only need a set of captioned images. At train time, our method learns to selectively align individual objects in an image with textual claims, without explicit supervision. At test time, we check if both captions correspond to the same object(s) in the image but are semantically different, which allows us to make fairly accurate out-of-context predictions. Our method achieves 85% out-of-context detection accuracy. To facilitate benchmarking of this task, we create a large-scale dataset of 200K images with 450K textual captions from a variety of news websites, blogs, and social media posts

We propose a novel method for high-quality facial texture reconstruction from RGB images using a novel capturing routine based on a single smartphone which we equip with an inexpensive polarization foil. Specifically, we turn the flashlight into a polarized light source and add a polarization filter on top of the camera. Leveraging this setup, we capture the face of a subject with cross-polarized and parallel-polarized light. For each subject, we record two short sequences in a dark environment under flash illumination with different light polarization using the modified smartphone. Based on these observations, we reconstruct an explicit surface mesh of the face using structure from motion. We then exploit the camera and light colocation within a differentiable renderer to optimize the facial textures using an analysis-by-synthesis approach. Our method optimizes for high-resolution normal textures, diffuse albedo, and specular albedo using a coarse-to-fine optimization scheme. We show that the optimized textures can be used in a standard rendering pipeline to synthesize high-quality photo-realistic 3D digital humans in novel environments.

We propose a novel 3D morphable model for complete human heads based on hybrid neural fields. At the core of our model lies a neural parametric representation that disentangles identity and expressions in disjoint latent spaces. To this end, we capture a person's identity in a canonical space as a signed distance field (SDF), and model facial expressions with a neural deformation field. In addition, our representation achieves high-fidelity local detail by introducing an ensemble of local fields centered around facial anchor points. To facilitate generalization, we train our model on a newly-captured dataset of over 3700 head scans from 203 different identities using a custom high-end 3D scanning setup. Our dataset significantly exceeds comparable existing datasets, both with respect to quality and completeness of geometry, averaging around 3.5M mesh faces per scan11We will publicly release our dataset along with a public benchmark for both neural head avatar construction as well as an evaluation on a hidden test-set for inference-time fitting.. Finally, we demonstrate that our approach outperforms state-of-the-art methods in terms of fitting error and reconstruction quality.

We present ObjectMatch11https://cangumeli.github.io/ObjectMatch/, a semantic and object-centric camera pose estimator for RGB-D SLAM pipelines. Modern camera pose estimators rely on direct correspondences of overlapping regions between frames; however, they cannot align camera frames with little or no overlap. In this work, we propose to leverage indirect correspondences obtained via semantic object identification. For instance, when an object is seen from the front in one frame and from the back in another frame, we can provide additional pose constraints through canonical object correspondences. We first propose a neural network to predict such correspondences on a per-pixel level, which we then combine in our energy formulation with state-of-the-art keypoint matching solved with a joint Gauss-Newton optimization. In a pairwise setting, our method improves registration recall of state-of-the-art feature matching, including from 24% to 45% in pairs with 10% or less inter-frame overlap. In registering RGB-D sequences, our method outperforms cutting-edge SLAM baselines in challenging, low-frame-rate scenarios, achieving more than 35% reduction in trajectory error in multiple scenes.

Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to per-ceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to leverage existing large-scale RGB-D data in a self-supervised pretraining to embed these 3D priors into 2D learned feature representations. In contrast to traditional 3D contrastive learning paradigms requiring 3D reconstructions or multi-view correspondences, our approach is simple: we formulate a pre-text reconstruction task by masking RGB and depth patches in individual RGB-D frames. We demonstrate the Mask3D is particularly effective in embedding 3D priors into the powerful 2D ViT backbone, enabling improved representation learning for various scene understanding tasks, such as semantic segmentation, instance segmentation and object detection. Experiments show that Mask3D notably outperforms existing self-supervised 3D pretraining approaches on ScanNet, NYUv2, and Cityscapes image understanding tasks, with an improvement of +6.5% mIoU against the state-of-the-art Pri3D on ScanNet image semantic segmentation.

We introduce DiffRF, a novel approach for 3D radiance field synthesis based on denoising diffusion probabilistic models. While existing diffusion-based methods operate on images, latent codes, or point cloud data, we are the first to directly generate volumetric radiance fields. To this end, we propose a 3D denoising model which directly operates on an explicit voxel grid representation. However, as radiance fields generated from a set of posed images can be ambiguous and contain artifacts, obtaining ground truth radiance field samples is non-trivial. We address this challenge by pairing the denoising formulation with a rendering loss, enabling our model to learn a deviated prior that favours good image quality instead of trying to replicate fitting errors like floating artifacts. In contrast to 2D-diffusion models, our model learns multi-view consistent priors, enabling free-view synthesis and accurate shape generation. Compared to 3D GANs, our diffusion-based approach naturally enables conditional generation such as masked completion or single-view 3D synthesis at inference time.

Holistic 3D scene understanding entails estimation of both layout configuration and object geometry in a 3D environment. Recent works have shown advances in 3D scene estimation from various input modalities (e.g., images, 3D scans), by leveraging 3D supervision (e.g., 3D bounding boxes or CAD models), for which collection at scale is ex-pensive and often intractable. To address this shortcoming, we propose a new method to learn 3D scene priors of layout and shape without requiring any 3D ground truth. Instead, we rely on 2D supervision from multi-view RGB images. Our method represents a 3D scene as a latent vector, from which we can progressively decode to a sequence of objects characterized by their class categories, 3D bounding boxes, and meshes. With our trained autoregressive decoder representing the scene prior, our method facilitates many downstream applications, including scene synthesis, interpolation, and single-view reconstruction. Experiments on 3D-FRONT and ScanNet show that our method outperforms state of the art in single-view reconstruction, and achieves state-of-the-art results in scene synthesis against baselines which require for 3D supervision. Project page: https://yinyunie.github.io/sceneprior-page/

We propose Panoptic Lifting, a novel approach for learning panoptic 3D volumetric representations from images of in-the-wild scenes. Once trained, our model can render color images together with 3D-consistent panoptic segmentation from novel viewpoints. Unlike existing approaches which use 3D input directly or indirectly, our method requires only machine-generated 2D panoptic segmentation masks inferred from a pre-trained network. Our core contribution is a panoptic lifting scheme based on a neural field representation that generates a unified and multi-view consistent, 3D panoptic representation of the scene. To account for inconsistencies of 2D instance identifiers across views, we solve a linear assignment with a cost based on the model's current predictions and the machine-generated segmentation masks, thus enabling us to lift 2D instances to 3D in a consistent way. We further propose and ablate contributions that make our method more robust to noisy, machine-generated labels, including test-time augmentations for confidence estimates, segment consistency loss, bounded segmentation fields, and gradient stopping. Experimental results validate our approach on the challenging Hypersim, Replica, and ScanNet datasets, improving by 8.4, 13.8, and 10.6% in scene-level PQ over state of the art.

Performing 3D dense captioning and visual grounding requires a common and shared understanding of the underlying multimodal relationships. However, despite some previous attempts on connecting these two related tasks with highly task-specific neural modules, it remains understudied how to explicitly depict their shared nature to learn them simultaneously. In this work, we propose UniT3D, a simple yet effective fully unified transformer-based architecture for jointly solving 3D visual grounding and dense captioning. UniT3D enables learning a strong multimodal representation across the two tasks through a supervised joint pre-training scheme with bidirectional and seq-to-seq objectives. With a generic architecture design, UniT3D allows expanding the pre-training scope to more various training sources such as the synthesized data from 2D prior knowledge to benefit 3D vision-language tasks. Extensive experiments and analysis demonstrate that UniT3D obtains significant gains for 3D dense captioning and visual grounding.

We present Text2Tex, a novel method for generating high-quality textures for 3D meshes from the given text prompts. Our method incorporates inpainting into a pre-trained depth-aware image diffusion model to progressively synthesize high resolution partial textures from multiple viewpoints. To avoid accumulating inconsistent and stretched artifacts across views, we dynamically segment the rendered view into a generation mask, which represents the generation status of each visible texel. This partitioned view representation guides the depth-aware inpainting model to generate and update partial textures for the corresponding regions. Furthermore, we propose an automatic view sequence generation scheme to determine the next best view for updating the partial texture. Extensive experiments demonstrate that our method significantly outperforms the existing text-driven approaches and GAN-based methods.

Implicit neural fields, typically encoded by a multilayer perceptron (MLP) that maps from coordinates (e.g., xyz) to signals (e.g., signed distances), have shown remarkable promise as a high-fidelity and compact representation. However, the lack of a regular and explicit grid structure also makes it challenging to apply generative modeling directly on implicit neural fields in order to synthesize new data. To this end, we propose HyperDiffusion, a novel approach for unconditional generative modeling of implicit neural fields. HyperDiffusion operates directly on MLP weights and generates new neural implicit fields encoded by synthesized MLP parameters. Specifically, a collection of MLPs is first optimized to faithfully represent individual data samples. Subsequently, a diffusion process is trained in this MLP weight space to model the underlying distribution of neural implicit fields. HyperDiffusion enables diffusion modeling over a implicit, compact, and yet high-fidelity representation of complex signals across 3D shapes and 4D mesh animations within one single unified framework.

We present Text2Room1, a method for generating room-scale textured 3D meshes from a given text prompt as input. To this end, we leverage pre-trained 2D text-to-image models to synthesize a sequence of images from different poses. In order to lift these outputs into a consistent 3D scene representation, we combine monocular depth estimation with a text-conditioned inpainting model. The core idea of our approach is a tailored viewpoint selection such that the content of each image can be fused into a seamless, textured 3D mesh. More specifically, we propose a continuous alignment strategy that iteratively fuses scene frames with the existing geometry to create a seamless mesh. Unlike existing works that focus on generating single objects [56], [41] or zoom-out trajectories [18] from text, our method generates complete 3D scenes with multiple objects and explicit 3D geometry. We evaluate our approach using qualitative and quantitative metrics, demonstrating it as the first method to generate room-scale 3D geometry with compelling textures from only text as input.

We propose a method for annotating videos of complex multi-object scenes with a globally-consistent 3D representation of the objects. We annotate each object with a CAD model from a database, and place it in the 3D coordinate frame of the scene with a 9-DoF pose transformation. Our method is semi-automatic and works on commonly-available RGB videos, without requiring a depth sensor. Many steps are performed automatically, and the tasks performed by humans are simple, well-specified, and require only limited reasoning in 3D. This makes them feasible for crowd-sourcing and has allowed us to construct a large-scale dataset by annotating real-estate videos from YouTube. Our dataset CAD-Estate offers 101k instances of 12k unique CAD models placed in the 3D representations of 20k videos. In comparison to Scan2CAD, the largest existing dataset with CAD model annotations on real scenes, CAD-Estate has 7× more instances and 4× more unique CAD models. We showcase the benefits of pre-training a Mask2CAD model on CAD-Estate for the task of automatic 3D object reconstruction and pose estimation, demonstrating that it leads to performance improvements on the popular Scan2CAD benchmark. The dataset is available at https://github.com/google-research/cad-estate.

Erroneous feature matches have severe impact on subsequent camera pose estimation and often require additional, time-costly measures, like RANSAC, for outlier rejection. Our method tackles this challenge by addressing feature matching and pose optimization jointly. To this end, we propose a graph attention network to predict image correspondences along with confidence weights. The resulting matches serve as weighted constraints in a differentiable pose estimation. Training feature matching with gradients from pose optimization naturally learns to downweight outliers and boosts pose estimation on image pairs compared to SuperGlue by 6.7% on ScanNet. At the same time, it reduces the pose estimation time by over 50% and renders RANSAC iterations unnecessary. Moreover, we integrate information from multiple views by spanning the graph across multiple frames to predict the matches all at once. Multi-view matching combined with end-to-end training improves the pose estimation metrics on Matterport3D by 18.5% compared to SuperGlue.

State-of-the-art face recognition systems require vast amounts of labeled training data. Given the priority of privacy in face recognition applications, the data is limited to celebrity web crawls, which have issues such as limited numbers of identities. On the other hand, self-supervised revolution in the industry motivates research on the adaptation of related techniques to facial recognition. One of the most popular practical tricks is to augment the dataset by the samples drawn from generative models while preserving the identity. We show that a simple approach based on fine-tuning pSp encoder for StyleGAN allows to improve upon the state-of-the-art facial recognition and performs better compared to training on synthetic face identities. We also collect large-scale unlabeled datasets with controllable ethnic constitution – AfricanFaceSet-5M (5 million images of different people) and AsianFaceSet-3M (3 million images of different people) – and we show that pretraining on each of them improves recognition of the respective ethnicities (as well as others), while combining all unlabeled datasets results in the biggest performance increase. Our self-supervised strategy is the most useful with limited amounts of labeled training data, which can be beneficial for more tailored face recognition tasks and when facing privacy concerns. Evaluation is based on a standard RFW dataset and a new large-scale RB-WebFace benchmark. The code and data are made publicly available at https://github.com/seva100/stylegan-for-facerec.

We present ScanNet++, a large-scale dataset that couples together capture of high-quality and commodity-level geometry and color of indoor scenes. Each scene is captured with a high-end laser scanner at sub-millimeter resolution, along with registered 33-megapixel images from a DSLR camera, and RGB-D streams from an iPhone. Scene reconstructions are further annotated with an open vocabulary of semantics, with label-ambiguous scenarios explicitly annotated for comprehensive semantic understanding. ScanNet++ enables a new real-world benchmark for novel view synthesis, both from high-quality RGB capture, and importantly also from commodity-level images, in addition to a new benchmark for 3D semantic scene understanding that comprehensively encapsulates diverse and ambiguous semantic labeling scenarios. Currently, ScanNet++ contains 460 scenes, 280,000 captured DSLR images, and over 3.7M iPhone RGBD frames.

We introduce a new diffusion-based approach for shape completion on 3D range scans. Compared with prior deterministic and probabilistic methods, we strike a balance between realism, multi-modality, and high fidelity. We propose DiffComplete by casting shape completion as a generative task conditioned on the incomplete shape. Our key designs are two-fold. First, we devise a hierarchical feature aggregation mechanism to inject conditional features in a spatially-consistent manner. So, we can capture both local details and broader contexts of the conditional inputs to control the shape completion. Second, we propose an occupancy-aware fusion strategy in our model to enable the completion of multiple partial shapes and introduce higher flexibility on the input conditions. DiffComplete sets a new SOTA performance (e.g., 40% decrease on $l_1$ error) on two large-scale 3D shape completion benchmarks. Our completed shapes not only have a realistic outlook compared with the deterministic methods but also exhibit high similarity to the ground truths compared with the probabilistic alternatives. Further, DiffComplete has strong generalizability on objects of entirely unseen classes for both synthetic and real data, eliminating the need for model re-training in various applications.

Recent Diffusion Transformers (i.e., DiT) have demonstrated their powerful effectiveness in generating high-quality 2D images. However, it is unclear how the Transformer architecture performs equally well in 3D shape generation, as previous 3D diffusion methods mostly adopted the U-Net architecture. To bridge this gap, we propose a novel Diffusion Transformer for 3D shape generation, named DiT-3D, which can directly operate the denoising process on voxelized point clouds using plain Transformers. Compared to existing U-Net approaches, our DiT-3D is more scalable in model size and produces much higher quality generations. Specifically, the DiT-3D adopts the design philosophy of DiT but modifies it by incorporating 3D positional and patch embeddings to aggregate input from voxelized point clouds. To reduce the computational cost of self-attention in 3D shape generation, we incorporate 3D window attention into Transformer blocks, as the increased 3D token length resulting from the additional dimension of voxels can lead to high computation. Finally, linear and devoxelization layers are used to predict the denoised point clouds. In addition, we empirically observe that the pre-trained DiT-2D checkpoint on ImageNet can significantly improve DiT-3D on ShapeNet. Experimental results on the ShapeNet dataset demonstrate that the proposed DiT-3D achieves state-of-the-art performance in high-fidelity and diverse 3D point cloud generation.

Indoor rooms are among the most common use cases in 3D scene understanding. Current state-of-the-art methods for this task are driven by large annotated datasets. Room layouts are especially important, consisting of structural elements in 3D, such as wall, floor, and ceiling. However, they are difficult to annotate, especially on pure RGB video. We propose a novel method to produce generic 3D room layouts just from 2D segmentation masks, which are easy to annotate for humans. Based on these 2D annotations, we automatically reconstruct 3D plane equations for the structural elements and their spatial extent in the scene, and connect adjacent elements at the appropriate contact edges. We annotate and publicly release 2246 3D room layouts on the RealEstate10k dataset, containing YouTube videos. We demonstrate the high quality of these 3D layouts annotations with extensive experiments.

We address the task of aligning CAD models to a video sequence of a complex scene containing multiple objects. Our method can process arbitrary videos and fully automatically recover the 9 DoF pose for each object appearing in it, thus aligning them in a common 3D coordinate frame. The core idea of our method is to integrate neural network predictions from individual frames with a temporally global, multi-view constraint optimization formulation. This integration process resolves the scale and depth ambiguities in the per-frame predictions, and generally improves the estimate of all pose parameters. By leveraging multi-view constraints, our method also resolves occlusions and handles objects that are out of view in individual frames, thus reconstructing all objects into a single globally consistent CAD representation of the scene. In comparison to the state-of-the-art single-frame method Mask2CAD that we build on, we achieve substantial improvements on the Scan2CAD dataset (from 11.6% to 30.7% class average accuracy).

In the last decade, deep learning (DL) has significantly impacted industry and science. Initially largely motivated by computer vision tasks in 2-D imagery, the focus has shifted toward 3-D data analysis. In particular, 3-D surface reconstruction, i.e., reconstructing a 3-D shape from sparse input, is of great interest to a large variety of application fields. DL-based approaches show promising quantitative and qualitative surface reconstruction performance compared to traditional computer vision and geometric algorithms. This survey provides a comprehensive overview of these DL-based methods for 3-D surface reconstruction. To this end, we will first discuss input data modalities, such as volumetric data, point clouds, and RGB, single-view, multiview, and depth images, along with corresponding acquisition technologies and common benchmark datasets. For practical purposes, we also discuss evaluation metrics enabling us to judge the reconstructive performance of different methods. The main part of the document will introduce a methodological taxonomy ranging from point-and mesh-based techniques to volumetric and implicit neural approaches. Recent research trends, both methodological and for applications, are highlighted, pointing toward future developments.

Representing human performance at high-fidelity is an essential building block in diverse applications, such as film production, computer games or videoconferencing. To close the gap to production-level quality, we introduce HumanRF 1 , a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints. Our novel representation acts as a dynamic video encoding that captures fine details at high compression rates by factorizing space-time into a temporal matrix-vector decomposition. This allows us to obtain temporally coherent reconstructions of human actors for long sequences, while representing high-resolution details even in the context of challenging motion. While most research focuses on synthesizing at resolutions of 4MP or lower, we address the challenge of operating at 12MP. To this end, we introduce ActorsHQ, a novel multi-view dataset that provides 12MP footage from 160 cameras for 16 sequences with high-fidelity, per-frame mesh reconstructions 2 . We demonstrate challenges that emerge from using such high-resolution data and show that our newly introduced HumanRF effectively leverages this data, making a significant step towards production-level quality novel view synthesis.

We focus on reconstructing high-fidelity radiance fields of human heads, capturing their animations over time, and synthesizing re-renderings from novel viewpoints at arbitrary time steps. To this end, we propose a new multi-view capture setup composed of 16 calibrated machine vision cameras that record time-synchronized images at 7.1 MP resolution and 73 frames per second. With our setup, we collect a new dataset of over 4700 high-resolution, high-framerate sequences of more than 220 human heads, from which we introduce a new human head reconstruction benchmark 1 . The recorded sequences cover a wide range of facial dynamics, including head motions, natural expressions, emotions, and spoken language. In order to reconstruct high-fidelity human heads, we propose Dynamic Neural Radiance Fields using Hash Ensembles (NeRSemble). We represent scene dynamics by combining a deformation field and an ensemble of 3D multi-resolution hash encodings. The deformation field allows for precise modeling of simple scene movements, while the ensemble of hash encodings helps to represent complex dynamics. As a result, we obtain radiance field representations of human heads that capture motion over time and facilitate re-rendering of arbitrary novel viewpoints. In a series of experiments, we explore the design choices of our method and demonstrate that our approach outperforms state-of-the-art dynamic radiance field approaches by a significant margin.

Neural Radiance Fields (NeRF) have shown impressive novel view synthesis results; nonetheless, even thorough recordings yield imperfections in reconstructions, for instance due to poorly observed areas or minor lighting changes. Our goal is to mitigate these imperfections from various sources with a joint solution: we take advantage of the ability of generative adversarial networks (GANs) to produce realistic images and use them to enhance realism in 3D scene reconstruction with NeRFs. To this end, we learn the patch distribution of a scene using an adversarial discriminator, which provides feedback to the radiance field reconstruction, thus improving realism in a 3D-consistent fashion. Thereby, rendering artifacts are repaired directly in the underlying 3D representation by imposing multi-view path rendering constraints. In addition, we condition a generator with multi-resolution NeRF renderings which is adversarially trained to further improve rendering quality. We demonstrate that our approach significantly improves rendering quality, e.g., nearly halving LPIPS scores compared to Nerfacto while at the same time improving PSNR by 1.4dB on the advanced indoor scenes of Tanks and Temples.

We introduce 3DShape2VecSet, a novel shape representation for neural fields designed for generative diffusion models. Our shape representation can encode 3D shapes given as surface models or point clouds, and represents them as neural fields. The concept of neural fields has previously been combined with a global latent vector, a regular grid of latent vectors, or an irregular grid of latent vectors. Our new representation encodes neural fields on top of a set of vectors. We draw from multiple concepts, such as the radial basis function representation, and the cross attention and self-attention function, to design a learnable representation that is especially suitable for processing with transformers. Our results show improved performance in 3D shape encoding and 3D shape generative modeling tasks. We demonstrate a wide variety of generative applications: unconditioned generation, category-conditioned generation, text-conditioned generation, point-cloud completion, and image-conditioned generation. Code: https://1zb.github.io/3DShape2VecSet/.

Obtaining high-quality 3D reconstructions of room-scale scenes is of paramount importance for upcoming applications in AR or VR. These range from mixed reality applications for teleconferencing, virtual measuring, virtual room planing, to robotic applications. While current volume-based view synthesis methods that use neural radiance fields (NeRFs) show promising results in reproducing the appearance of an object or scene, they do not reconstruct an actual surface. The volumetric representation of the surface based on densities leads to artifacts when a surface is extracted using Marching Cubes, since during optimization, densities are accumulated along the ray and are not used at a single sample point in isolation. Instead of this volumetric representation of the surface, we propose to represent the surface using an implicit function (truncated signed distance function). We show how to incorporate this representation in the NeRF framework, and extend it to use depth measurements from a commodity RGB-D sensor, such as a Kinect. In addition, we propose a pose and camera re-finement technique which improves the overall reconstruction quality. In contrast to concurrent work on integrating depth priors in NeRF which concentrates on novel view synthesis, our approach is able to reconstruct high-quality, metrical 3D reconstructions.

We present Neural Head Avatars, a novel neural representation that explicitly models the surface geometry and appearance of an animatable human avatar that can be used for teleconferencing in AR/VR or other applications in the movie or games industry that rely on a digital human.11philgras.github.io/neural_head_avatars/neural_head_avatars.html Our representation can be learned from a monocular RGB portrait video that features a range of different expressions and views. Specifically, we propose a hybrid representation consisting of a morphable model for the coarse shape and expressions of the face, and two feed-forward networks, predicting vertex offsets of the underlying mesh as well as a view- and expression-dependent texture. We demonstrate that this representation is able to accurately extrapolate to unseen poses and view points, and generates natural expressions while providing sharp texture details. Compared to previous works on head avatars, our method provides a disentangled shape and appearance model of the complete human head (including hair) that is compatible with the standard graphics pipeline. Moreover, it quantitatively and qualitatively outperforms current state of the art in terms of reconstruction quality and novel-view synthesis.

We present ROCA11The code is made available at https://github.com/cangurneli/ROCA., a novel end-to-end approach that re-trieves and aligns 3D CAD models from a shape database to a single input image. This enables 3D perception of an ob-served scene from a 2D RGB observation, characterized as a lightweight, compact, clean CAD representation. Core to our approach is our differentiable alignment optimization based on dense 2D-3D object correspondences and Pro-crustes alignment. ROCA can thus provide a robust CAD alignment while simultaneously informing CAD retrieval by leveraging the 2D-3D correspondences to learn geometri-cally similar CAD models. Experiments on challenging, real-world imagery from ScanNet show that ROCA signif-icantly improves on state of the art, from 9.5% to 17.6% in retrieval-aware CAD alignment accuracy.

We apply style transfer on mesh reconstructions of indoor scenes. This enables VR applications like experiencing 3D environments painted in the style of a favorite artist. Style transfer typically operates on 2D images, making stylization of a mesh challenging. When optimized over a variety of poses, stylization patterns become stretched out and inconsistent in size. On the other hand, model-based 3D style transfer methods exist that allow stylization from a sparse set of images, but they require a network at inference time. To this end, we optimize an explicit texture for the reconstructed mesh of a scene and stylize it jointly from all available input images. Our depth- and angle-aware optimization leverages surface normal and depth data of the underlying mesh to create a uniform and consistent stylization for the whole scene. Our experiments show that our method creates sharp and detailed results for the complete scene without view-dependent artifacts. Through extensive ablation studies, we show that the proposed 3D awareness enables style transfer to be applied to the 3D domain of a mesh. Our method11https://lukashoel.github.io/stylemesh/ can be used to render a stylized mesh in real-time with traditional rendering pipelines.

We introduce AutoRF - a new approach for learning neural 3D object representations where each object in the training set is observed by only a single view. This setting is in stark contrast to the majority of existing works that leverage multiple views of the same object, employ explicit priors during training, or require pixel-perfect annotations. To address this challenging setting, we propose to learn a normalized, object-centric representation whose embedding describes and disentangles shape, appearance, and pose. Each encoding provides well-generalizable, compact information about the object of interest, which is decoded in a single-shot into a new target view, thus enabling novel view synthesis. We further improve the reconstruction quality by optimizing shape and appearance codes at test time by fitting the representation tightly to the input image. In a series of experiments, we show that our method generalizes well to unseen objects, even across different datasets of challenging real-world street scenes such as nuScenes, KITTI, and Mapillary Metropolis. Additional results can be found on our project page https://sirwyver.github.io/AutoRF/.

Neural radiance fields (NeRF) encode a scene into a neural representation that enables photo-realistic rendering of novel views. However, a successful reconstruction from RGB images requires a large number of input views taken under static conditions — typically up to a few hundred images for room-size scenes. Our method aims to synthesize novel views of whole rooms from an order of magnitude fewer images. To this end, we leverage dense depth priors in order to constrain the NeRF optimization. First, we take advantage of the sparse depth data that is freely available from the structure from motion (SfM) preprocessing step used to estimate camera poses. Second, we use depth completion to convert these sparse points into dense depth maps and uncertainty estimates, which are used to guide NeRF optimization. Our method enables data-efficient novel view synthesis on challenging indoor scenes, using as few as 18 images for an entire scene.

Convolutional neural networks were the standard for solving many computer vision tasks until recently, when Transformers of MLP-based architectures have started to show competitive performance. These architectures typically have a vast number of weights and need to be trained on massive datasets; hence, they are not suitable for their use in low-data regimes. In this work, we propose a simple yet effective framework to improve generalization from small amounts of data. We augment modern CNNs with fully-connected (FC) layers and show the massive impact this architectural change has in low-data regimes. We further present an online joint knowledge-distillation method to utilize the extra FC layers at train time but avoid them during test time. This allows us to improve the generalization of a CNN-based model without any increase in the number of weights at test time. We perform classification experiments for a large range of network backbones and several standard datasets on supervised learning and active learning. Our experiments significantly outperform the networks without fully-connected layers, reaching a relative improvement of up to $16\%$ validation accuracy in the supervised setting without adding any extra parameters during inference.

We propose a new representation for encoding 3D shapes as neural fields. The representation is designed to be compatible with the transformer architecture and to benefit both shape reconstruction and shape generation. Existing works on neural fields are grid-based representations with latents being defined on a regular grid. In contrast, we define latents on irregular grids which facilitates our representation to be sparse and adaptive. In the context of shape reconstruction from point clouds, our shape representation built on irregular grids improves upon grid-based methods in terms of reconstruction accuracy. For shape generation, our representation promotes high-quality shape generation using auto-regressive probabilistic models. We show different applications that improve over the current state of the art. First, we show results of probabilistic shape reconstruction from a single higher resolution image. Second, we train a probabilistic model conditioned on very low resolution images. Third, we apply our model to category-conditioned generation. All probabilistic experiments confirm that we are able to generate detailed and high quality shapes to yield the new state of the art in generative 3D shape modeling.

We present Neural Shape Deformation Priors, a novel method for shape manipulation that predicts mesh deformations of non-rigid objects from user-provided handle movements. State-of-the-art methods cast this problem as an optimization task, where the input source mesh is iteratively deformed to minimize an objective function according to hand-crafted regularizers such as ARAP. In this work, we learn the deformation behavior based on the underlying geometric properties of a shape, while leveraging a large-scale dataset containing a diverse set of non-rigid deformations. Specifically, given a source mesh and desired target locations of handles that describe the partial surface deformation, we predict a continuous deformation field that is defined in 3D space to describe the space deformation. To this end, we introduce transformer-based deformation networks that represent a shape deformation as a composition of local surface deformations. It learns a set of local latent codes anchored in 3D space, from which we can learn a set of continuous deformation functions for local surfaces. Our method can be applied to challenging deformations and generalizes well to unseen deformations. We validate our approach in experiments using the DeformingThing4D dataset, and compare to both classic optimization-based and recent neural network-based methods.

Neural radiance fields (NeRF) have shown great success in modeling 3D scenes and synthesizing novel-view images. However, most previous NeRF methods take much time to optimize one single scene. Explicit data structures, e.g. voxel features, show great potential to accelerate the training process. However, voxel features face two big challenges to be applied to dynamic scenes, i.e. modeling temporal information and capturing different scales of point motions. We propose a radiance field framework by representing scenes with time-aware voxel features, named as TiNeuVox. A tiny coordinate deformation network is introduced to model coarse motion trajectories and temporal information is further enhanced in the radiance network. A multi-distance interpolation method is proposed and applied on voxel features to model both small and large motions. Our framework significantly accelerates the optimization of dynamic radiance fields while maintaining high rendering quality. Empirical evaluation is performed on both synthetic and real scenes. Our TiNeuVox completes training with only 8 minutes and 8-MB storage cost while showing similar or even better rendering performance than previous dynamic NeRF methods. Code is available at https://github.com/hustvl/TiNeuVox.

Abstract Synthesizing photo‐realistic images and videos is at the heart of computer graphics and has been the focus of decades of research. Traditionally, synthetic images of a scene are generated using rendering algorithms such as rasterization or ray tracing, which take specifically defined representations of geometry and material properties as input. Collectively, these inputs define the actual scene and what is rendered, and are referred to as the scene representation (where a scene consists of one or more objects). Example scene representations are triangle meshes with accompanied textures (e.g., created by an artist), point clouds (e.g., from a depth sensor), volumetric grids (e.g., from a CT scan), or implicit surface functions (e.g., truncated signed distance fields). The reconstruction of such a scene representation from observations using differentiable rendering losses is known as inverse graphics or inverse rendering. Neural rendering is closely related, and combines ideas from classical computer graphics and machine learning to create algorithms for synthesizing images from real‐world observations. Neural rendering is a leap forward towards the goal of synthesizing photo‐realistic image and video content. In recent years, we have seen immense progress in this field through hundreds of publications that show different ways to inject learnable components into the rendering pipeline. This state‐of‐the‐art report on advances in neural rendering focuses on methods that combine classical rendering principles with learned 3D scene representations, often now referred to as neural scene representations. A key advantage of these methods is that they are 3D‐consistent by design, enabling applications such as novel viewpoint synthesis of a captured scene. In addition to methods that handle static scenes, we cover neural scene representations for modeling non‐rigidly deforming objects and scene editing and composition. While most of these approaches are scene‐specific, we also discuss techniques that generalize across object classes and can be used for generative tasks. In addition to reviewing these state‐of‐the‐art methods, we provide an overview of fundamental concepts and definitions used in the current literature. We conclude with a discussion on open challenges and social implications.

We address the task of indoor scene generation by generating a sequence of objects, along with their locations and orientations conditioned on a room layout. Large-scale indoor scene datasets allow us to extract patterns from user-designed indoor scenes, and generate new scenes based on these patterns. Existing methods rely on the 2D or 3D appearance of these scenes in addition to object positions, and make assumptions about the possible relations between objects. In contrast, we do not use any appearance information, and implicitly learn object relations using the self-attention mechanism of transformers. We show that our model design leads to faster scene generation with similar or improved levels of realism compared to previous methods. Our method is also flexible, as it can be conditioned not only on the room layout but also on text descriptions of the room, using only the cross-attention mechanism of transformers. Our user study shows that our generated scenes are preferred to the state-of-the-art FastSynth scenes 53.9% and 56.7% of the time for bedroom and living room scenes, respectively. At the same time, we generate a scene in 1.48 seconds on average, 20% faster than FastSynth.

Self-attention networks have shown remarkable progress in computer vision tasks such as image classification. The main benefit of the self-attention mechanism is the ability to capture long-range feature interactions in attention-maps. However, the computation of attention-maps requires a learnable key, query, and positional encoding, whose usage is often not intuitive and computationally expensive. To mitigate this problem, we propose a novel self-attention module with explicitly modeled attention-maps using only a single learnable parameter for low computational overhead. The design of explicitly modeled attention-maps using geometric prior is based on the observation that the spatial context for a given pixel within an image is mostly dominated by its neighbors, while more distant pixels have a minor contribution. Concretely, the attention-maps are parametrized via simple functions (e.g., Gaussian kernel) with a learnable radius, which is modeled independently of the input content. Our evaluation shows that our method achieves an accuracy improvement of up to 2.2% over the ResNet-baselines in ImageNet ILSVRC and outperforms other self-attention methods such as AA-ResNet152 in accuracy by 0.9% with 6.4% fewer parameters and 6.7% fewer GFLOPs. This result empirically indicates the value of incorporating geometric prior into self-attention mechanism when applied in image classification.

We introduce Neural Deformation Graphs for globally-consistent deformation tracking and 3D reconstruction of non-rigid objects. Specifically, we implicitly model a deformation graph via a deep neural network. This neural deformation graph does not rely on any object-specific structure and, thus, can be applied to general non-rigid deformation tracking. Our method globally optimizes this neural graph on a given sequence of depth camera observations of a non-rigidly moving object. Based on explicit viewpoint consistency as well as inter-frame graph and surface consistency constraints, the underlying network is trained in a self-supervised fashion. We additionally optimize for the geometry of the object with an implicit deformable multi-MLP shape representation. Our approach does not assume sequential input data, thus enabling robust tracking of fast motions or even temporally disconnected recordings. Our experiments demonstrate that our Neural Deformation Graphs outperform state-of-the-art non-rigid reconstruction approaches both qualitatively and quantitatively, with 64% improved reconstruction and 54% improved deformation tracking performance. Code is publicly available.1

We introduce the task of dense captioning in 3D scans from commodity RGB-D sensors. As input, we assume a point cloud of a 3D scene; the expected output is the bounding boxes along with the descriptions for the underlying objects. To address the 3D object detection and description problems, we propose Scan2Cap, an end-to-end trained method, to detect objects in the input scene and describe them in natural language. We use an attention mechanism that generates descriptive tokens while referring to the related components in the local context. To reflect object relations (i.e. relative spatial relations) in the generated captions, we use a message passing graph module to facilitate learning object relation features. Our method can effectively localize and describe 3D objects in scenes from the ScanRefer dataset, outperforming 2D baseline methods by a significant margin (27.61% [email protected] improvement).

We present SPSG, a novel approach to generate high-quality, colored 3D models of scenes from RGB-D scan observations by learning to infer unobserved scene geometry and color in a self-supervised fashion. Our self-supervised approach learns to jointly inpaint geometry and color by correlating an incomplete RGB-D scan with a more complete version of that scan. Notably, rather than relying on 3D reconstruction losses to inform our 3D geometry and color reconstruction, we propose adversarial and perceptual losses operating on 2D renderings in order to achieve high-resolution, high-quality colored reconstructions of scenes. This exploits the high-resolution, self-consistent signal from individual raw RGB-D frames, in contrast to fused 3D reconstructions of the frames which exhibit inconsistencies from view-dependent effects, such as color balancing or pose inconsistencies. Thus, by informing our 3D scene generation directly through 2D signal, we produce high-quality colored reconstructions of 3D scenes, outperforming state of the art on both synthetic and real data.

We present dynamic neural radiance fields for modeling the appearance and dynamics of a human face1. Digitally modeling and reconstructing a talking human is a key building-block for a variety of applications. Especially, for telepresence applications in AR or VR, a faithful reproduction of the appearance including novel viewpoint or headposes is required. In contrast to state-of-the-art approaches that model the geometry and material properties explicitly, or are purely image-based, we introduce an implicit representation of the head based on scene representation networks. To handle the dynamics of the face, we combine our scene representation network with a low-dimensional morphable model which provides explicit control over pose and expressions. We use volumetric rendering to generate images from this hybrid representation and demonstrate that such a dynamic neural scene representation can be learned from monocular input data only, without the need of a specialized capture setup. In our experiments, we show that this learned volumetric representation allows for photorealistic image generation that surpasses the quality of state-of-the-art video-based reenactment methods.

The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and an-notating 3D scenes (e.g. point clouds) are notoriously hard. For example, the number of scenes (e.g. indoor rooms) that can be accessed and scanned might be limited; even given sufficient data, acquiring 3D labels (e.g. instance masks) requires intensive human labor. In this paper, we explore data-efficient learning for 3D point cloud. As a first step towards this direction, we propose Contrastive Scene Contexts, a 3D pre-training method that makes use of both point-level correspondences and spatial contexts in a scene. Our method achieves state-of-the-art results on a suite of benchmarks where training data or labels are scarce. Our study reveals that exhaustive labelling of 3D point clouds might be unnecessary; and remarkably, on ScanNet, even using 0.1% of point labels, we still achieve 89% (instance segmentation) and 96% (semantic segmentation) of the baseline performance that uses full annotations.

Multi-object tracking from RGB-D video sequences is a challenging problem due to the combination of changing viewpoints, motion, and occlusions over time. We observe that having the complete geometry of objects aids in their tracking, and thus propose to jointly infer the complete geometry of objects as well as track them, for rigidly moving objects over time. Our key insight is that inferring the complete geometry of the objects significantly helps in tracking. By hallucinating unseen regions of objects, we can obtain additional correspondences between the same instance, thus providing robust tracking even under strong change of appearance. From a sequence of RGB-D frames, we detect objects in each frame and learn to predict their complete object geometry as well as a dense correspondence mapping into a canonical space. This allows us to derive 6DoF poses for the objects in each frame, along with their correspondence between frames, providing robust object tracking across the RGB-D sequence. Experiments on both synthetic and real-world RGB-D data demonstrate that we achieve state-of-the-art performance on dynamic object tracking. Furthermore, we show that our object completion significantly helps tracking, providing an improvement of 6.5% in mean MOTA.

Semantic scene understanding from point clouds is particularly challenging as the points reflect only a sparse set of the underlying 3D geometry. Previous works often convert point cloud into regular grids (e.g. voxels or bird-eye view images), and resort to grid-based convolutions for scene understanding. In this work, we introduce RfD-Net that jointly detects and reconstructs dense object surfaces directly from raw point clouds. Instead of representing scenes with regular grids, our method leverages the sparsity of point cloud data and focuses on predicting shapes that are recognized with high objectness. With this design, we decouple the instance reconstruction into global object localization and local shape prediction. It not only eases the difficulty of learning 2-D manifold surfaces from sparse 3D space, the point clouds in each object proposal convey shape details that support implicit function learning to reconstruct any high-resolution surfaces. Our experiments indicate that instance detection and reconstruction present complementary effects, where the shape prediction head shows consistent effects on improving object detection with modern 3D proposal network backbones. The qualitative and quantitative evaluations further demonstrate that our approach consistently outperforms the state-of-the-arts and improves over 11 of mesh IoU in object reconstruction.

We present a novel method for temporal coherent reconstruction and tracking of clothed humans. Given a monocular RGB-D sequence, we learn a person-specific body model which is based on a dynamic surface function network. To this end, we explicitly model the surface of the person using a multi-layer perceptron (MLP) which is embedded into the canonical space of the SMPL body model. With classical forward rendering, the represented surface can be rasterized using the topology of a template mesh. For each surface point of the template mesh, the MLP is evaluated to predict the actual surface location. To handle pose-dependent deformations, the MLP is conditioned on the SMPL pose parameters. We show that this surface representation as well as the pose parameters can be learned in a self-supervised fashion using the principle of analysis-by-synthesis and differentiable rasterization. As a result, we are able to reconstruct a temporally coherent mesh sequence from the input data. The underlying surface representation can be used to synthesize new animations of the reconstructed person including pose-dependent deformations.

A major challenge in DeepFake forgery detection is that state-of-the-art algorithms are mostly trained to detect a specific fake method. As a result, these approaches show poor generalization across different types of facial manipulations, e.g., from face swapping to facial reenactment. To this end, we introduce ID-Reveal, a new approach that learns temporal facial features, specific of how a person moves while talking, by means of metric learning coupled with an adversarial training strategy. The advantage is that we do not need any training data of fakes, but only train on real videos. Moreover, we utilize high-level semantic features, which enables robustness to widespread and disruptive forms of post-processing. We perform a thorough experimental analysis on several publicly available benchmarks. Compared to state of the art, our method improves generalization and is more robust to low-quality videos, that are usually spread over social networks. In particular, we obtain an average improvement of more than 15% in terms of accuracy for facial reenactment on high compressed videos.

Recent advances in 3D perception have shown impressive progress in understanding geometric structures of 3D shapes and even scenes. Inspired by these advances in geometric understanding, we aim to imbue image-based perception with representations learned under geometric constraints. We introduce an approach to learn view-invariant, geometry-aware representations for network pre-training, based on multi-view RGB-D data, that can then be effectively transferred to downstream 2D tasks. We propose to employ contrastive learning under both multi-view image constraints and image-geometry constraints to encode 3D priors into learned 2D representations. This results not only in improvement over 2D-only representation learning on the image-based tasks of semantic segmentation, instance segmentation and object detection on real-world indoor datasets, but moreover, provides significant improvement in the low data regime. We show significant improvement of 6.0% on semantic segmentation on full data as well as 11.9% on 20% data against baselines on ScanNet. Our code is open sourced at https://github.com/Sekunde/Pri3D.

Tracking non-rigidly deforming scenes using range sensors has numerous applications including computer vision, AR/VR, and robotics. However, due to occlusions and physical limitations of range sensors, existing methods only handle the visible surface, thus causing discontinuities and in-completeness in the motion field. To this end, we introduce 4DComplete, a novel data-driven approach that estimates the non-rigid motion for the unobserved geometry. 4DComplete takes as input a partial shape and motion observation, extracts 4D time-space embedding, and jointly infers the missing geometry and motion field using a sparse fully-convolutional network. For network training, we constructed a large-scale synthetic dataset called DeformingThings4D, which consists of 1,972 animation sequences spanning 31 different animals or humanoid categories with dense 4D annotation. Experiments show that 4DComplete 1) reconstructs high-resolution volumetric shape and motion field from a partial observation, 2) learns an entangled 4D feature representation that benefits both shape and motion estimation, 3) yields more accurate and natural deformation than classic non-rigid priors such as As-Rigid-As-Possible (ARAP) deformation, and 4) generalizes well to unseen objects in real-world sequences.

Parametric 3D models have enabled a wide variety of tasks in computer graphics and vision, such as modeling human bodies, faces, and hands. However, the construction of these parametric models is often tedious, as it requires heavy manual tweaking, and they struggle to represent additional complexity and details such as wrinkles or clothing. To this end, we propose Neural Parametric Models (NPMs), a novel, learned alternative to traditional, parametric 3D models, which does not require handcrafted, object-specific constraints. In particular, we learn to disentangle 4D dynamics into latent-space representations of shape and pose, leveraging the flexibility of recent developments in learned implicit functions. Crucially, once learned, our neural parametric models of shape and pose enable optimization over the learned spaces to fit to new observations, similar to the fitting of a traditional parametric model, e.g., SMPL. This enables NPMs to achieve a significantly more accurate and detailed representation of observed deformable sequences. We show that NPMs improve notably over both parametric and non-parametric state of the art in reconstruction and tracking of monocular depth sequences of clothed humans and hands. Latent-space interpolation as well as shape / pose transfer experiments further demonstrate the usefulness of NPMs. Code is publicly available at https://pablopalafox.github.io/npms.

3D reconstruction of large scenes is a challenging problem due to the high-complexity nature of the solution space, in particular for generative neural networks. In contrast to traditional generative learned models which encode the full generative process into a neural network and can struggle with maintaining local details at the scene level, we introduce a new method that directly leverages scene geometry from the training database. First, we learn to synthesize an initial estimate for a 3D scene, constructed by retrieving a top-k set of volumetric chunks from the scene database. These candidates are then refined to a final scene generation with an attention-based refinement that can effectively select the most consistent set of geometry from the candidates and combine them together to create an output scene, facilitating transfer of coherent structures and local detail from train scene geometry. We demonstrate our neural scene reconstruction with a database for the tasks of 3D super resolution and surface reconstruction from sparse point clouds, showing that our approach enables generation of more coherent, accurate 3D scenes, improving on average by over 8% in IoU over state-of-the-art scene reconstruction.

We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach. From an input monocular RGB video, the video frames are processed by a transformer network that fuses the observations into a volumetric feature grid representing the scene; this feature grid is then decoded into an implicit 3D scene representation. Key to our approach is the transformer architecture that enables the network to learn to attend to the most relevant image frames for each 3D location in the scene, supervised only by the scene reconstruction task. Features are fused in a coarse-to-fine fashion, storing fine-level features only where needed, requiring lower memory storage and enabling fusion at interactive rates. The feature grid is then decoded to a higher-resolution scene reconstruction, using an MLP-based surface occupancy prediction from interpolated coarse-to-fine 3D features. Our approach results in an accurate surface reconstruction, outperforming state-of-the-art multi-view stereo depth estimation methods, fully-convolutional 3D reconstruction approaches, and approaches using LSTM- or GRU-based recurrent networks for video sequence fusion.

Richly segmented 3D scene reconstructions are an integral basis for many high-level scene understanding tasks, such as for robotics, motion planning, or augmented reality. Existing works in 3D perception from a single RGB image tend to focus on geometric reconstruction only, or geometric reconstruction with semantic segmentation or instance segmentation.Inspired by 2D panoptic segmentation, we propose to unify the tasks of geometric reconstruction, 3D semantic segmentation, and 3D instance segmentation into the task of panoptic 3D scene reconstruction -- from a single RGB image, predicting the complete geometric reconstruction of the scene in the camera frustum of the image, along with semantic and instance segmentations.We propose a new approach for holistic 3D scene understanding from a single RGB image which learns to lift and propagate 2D features from an input image to a 3D volumetric scene representation.Our panoptic 3D reconstruction metric evaluates both geometric reconstruction quality as well as panoptic segmentation.Our experiments demonstrate that our approach for panoptic 3D scene reconstruction outperforms alternative approaches for this task.

Abstract Although surface reconstruction from depth data has made significant advances in the recent years, handling changing environments remains a major challenge. This is unsatisfactory, as humans regularly move objects in their environments. Existing solutions focus on a restricted set of objects (e.g., those detected by semantic classifiers) possibly with template meshes, assume static camera, or mark objects touched by humans as moving. We remove these assumptions by introducing RigidFusion. Our core idea is a novel asynchronous moving‐object detection method, combined with a modified volumetric fusion. This is achieved by a model‐to‐frame TSDF decomposition leveraging free‐space carving of tracked depth values of the current frame with respect to the background model during run‐time. As output, we produce separate volumetric reconstructions for the background and each moving object in the scene, along with its trajectory over time. Our method does not rely on the object priors (e.g., semantic labels or pre‐scanned meshes) and is insensitive to the motion residuals between objects and the camera. In comparison to state‐of‐the‐art methods (e.g., Co‐Fusion, MaskFusion), we handle significantly more challenging reconstruction scenarios involving moving camera and improve moving‐object detection (26% on the miss‐detection ratio), tracking (27% on MOTA), and reconstruction (3% on the reconstruction F1) on the synthetic dataset. Please refer the supplementary and the project website for the video demonstration ( geometry.cs.ucl.ac.uk/projects/2021/rigidfusion ).

Large-scale optimization problems at the core of many graphics, vision, and imaging applications are often implemented by hand in tedious and error-prone processes in order to achieve high performance (in particular on GPUs), despite recent developments in libraries and DSLs. At the same time, these hand-crafted solver implementations reveal that the key for high performance is a problem-specific schedule that enables efficient usage of the underlying hardware. In this work, we incorporate this insight into Thallo, a domain-specific language for large-scale non-linear least squares optimization problems. We observe various code reorganizations performed by implementers of high-performance solvers in the literature, and then define a set of basic operations that span these scheduling choices, thereby defining a large scheduling space. Users can either specify code transformations in a scheduling language or use an autoscheduler. Thallo takes as input a compact, shader-like representation of an energy function and a (potentially auto-generated) schedule, translating the combination into high-performance GPU solvers. Since Thallo can generate solvers from a large scheduling space, it can handle a large set of large-scale non-linear and non-smooth problems with various degrees of non-locality and compute-to-memory ratios, including diverse applications such as bundle adjustment, face blendshape fitting, and spatially-varying Poisson deconvolution, as seen in Figure 1. Abstracting schedules from the optimization, we outperform state-of-the-art GPU-based optimization DSLs by an average of 16× across all applications introduced in this work, and even some published hand-written GPU solvers by 30%+.

Neural rendering techniques promise efficient photorealistic image synthesis while providing rich control over scene parameters by learning the physical image formation process. While several supervised methods have been proposed for this task, acquiring a dataset of images with accurately aligned 3D models is very difficult. The main contribution of this work is to lift this restriction by training a neural rendering algorithm from unpaired data. We propose an autoencoder for joint generation of realistic images from synthetic 3D models while simultaneously decomposing real images into their intrinsic shape and appearance properties. In contrast to a traditional graphics pipeline, our approach does not require to specify all scene properties, such as material parameters and lighting by hand. Instead, we learn photo-realistic deferred rendering from a small set of 3D models and a larger set of unaligned real images, both of which are easy to acquire in practice. Simultaneously, we obtain accurate intrinsic decompositions of real images while not requiring paired ground truth. Our experiments confirm that a joint treatment of rendering and decomposition is indeed beneficial and that our approach outperforms state-of-the-art image-to-image translation baselines both qualitatively and quantitatively.

Applying data-driven approaches to non-rigid 3D reconstruction has been difficult, which we believe can be attributed to the lack of a large-scale training corpus. Unfortunately, this method fails for important cases such as highly non-rigid deformations. We first address this problem of lack of data by introducing a novel semi-supervised strategy to obtain dense inter-frame correspondences from a sparse set of annotations. This way, we obtain a large dataset of 400 scenes, over 390,000 RGB-D frames, and 5,533 densely aligned frame pairs; in addition, we provide a test set along with several metrics for evaluation. Based on this corpus, we introduce a data-driven non-rigid feature matching approach, which we integrate into an optimization-based reconstruction pipeline. Here, we propose a new neural network that operates on RGB-D frames, while maintaining robustness under large non-rigid deformations and producing accurate predictions. Our approach significantly outperforms existing non-rigid reconstruction methods that do not use learned data terms, as well as learning-based approaches that only use self-supervision.

We present a novel approach that converts partial and noisy RGB-D scans into high-quality 3D scene reconstructions by inferring unobserved scene geometry. Our approach is fully self-supervised and can hence be trained solely on incomplete, real-world scans. To achieve, self-supervision, we remove frames from a given (incomplete) 3D scan in order to make it even more incomplete; self-supervision is then formulated by correlating the two levels of partialness of the same scan while masking out regions that have never been observed. Through generalization across a large training set, we can then predict 3D scene completions even without seeing any 3D scan of entirely complete geometry. Combined with a new 3D sparse generative convolutional neural network architecture, our method is able to predict highly detailed surfaces in a coarse-to-fine hierarchical fashion that outperform existing state-of-the-art methods by a significant margin in terms of reconstruction quality.

We present 3D-MPA, a method for instance segmentation on 3D point clouds. Given an input point cloud, we propose an object-centric approach where each point votes for its object center. We sample object proposals from the predicted object centers. Then, we learn proposal features from grouped point features that voted for the same object center. A graph convolutional network introduces inter-proposal relations, providing higher-level feature learning in addition to the lower-level point features. Each proposal comprises a semantic label, a set of associated points over which we define a foreground-background mask, an objectness score and aggregation features. Previous works usually perform non-maximum-suppression (NMS) over proposals to obtain the final object detections or semantic instances. However, NMS can discard potentially correct predictions. Instead, our approach keeps all proposals and groups them together based on the learned aggregation features. We show that grouping proposals improves over NMS and outperforms previous state-of-the-art methods on the tasks of 3D object detection and semantic instance segmentation on the ScanNetV2 benchmark and the S3DIS dataset.

During 3D reconstruction, it is often the case that people cannot scan each individual object from all views, resulting in missing geometry in the captured scan. This missing geometry can be fundamentally limiting for many applications, e.g., a robot needs to know the unseen geometry to perform a precise grasp on an object. Thus, we introduce the task of semantic instance completion: from an incomplete RGB-D scan of a scene, we aim to detect the individual object instances and infer their complete object geometry. This will open up new possibilities for interactions with objects in a scene, for instance for virtual or robotic agents. We tackle this problem by introducing RevealNet, a new data-driven approach that jointly detects object instances and predicts their complete geometry. This enables a semantically meaningful decomposition of a scanned scene into individual, complete 3D objects, including hidden and unobserved object parts. RevealNet is an end-to-end 3D neural network architecture that leverages joint color and geometry feature learning. The fully-convolutional nature of our 3D network enables efficient inference of semantic instance completion for 3D scans at scale of large indoor environments in a single forward pass. We show that predicting complete object geometry improves both 3D detection and instance segmentation performance. We evaluate on both real and synthetic scan benchmark data for the new task, where we outperform state-of-the-art approaches by over 15 in [email protected] on ScanNet, and over 18 in [email protected] on SUNCG.

Realistic color texture generation is an important step in RGB-D surface reconstruction, but remains challenging in practice due to inaccuracies in reconstructed geometry, misaligned camera poses, and view-dependent imaging artifacts. In this work, we present a novel approach for color texture generation using a conditional adversarial loss obtained from weakly-supervised views. Specifically, we propose an approach to produce photorealistic textures for approximate surfaces, even from misaligned images, by learning an objective function that is robust to these errors. The key idea of our approach is to learn a patch-based conditional discriminator which guides the texture optimization to be tolerant to misalignments. Our discriminator takes a synthesized view and a real image, and evaluates whether the synthesized one is realistic, under a broadened definition of realism. We train the discriminator by providing as `real' examples pairs of input views and their misaligned versions - so that the learned adversarial loss will tolerate errors from the scans. Experiments on synthetic and real data under quantitative or qualitative evaluation demonstrate the advantage of our approach in comparison to state of the art (see Figure 1, right). Our code is publicly available1with video demonstration2.

Shape priors learned from data are commonly used to reconstruct 3D objects from partial or noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D autoencoders cannot handle their scale, complexity, or diversity. In this paper, we introduce Local Implicit Grid Representations, a new 3D shape representation designed for scalability and generality. The motivating idea is that most 3D surfaces share geometric details at some scale - i.e., at a scale smaller than an entire object and larger than a small patch. We train an autoencoder to learn an embedding of local crops of 3D shapes at that size. Then, we use the decoder as a component in a shape optimization that solves for a set of latent codes on a regular grid of overlapping crops such that an interpolation of the decoded local shapes matches a partial or noisy observation. We demonstrate the value of this proposed approach for 3D surface reconstruction from sparse point observations, showing significantly better results than alternative approaches.

One of the widespread solutions for non-rigid tracking has a nested-loop structure: with Gauss-Newton to minimize a tracking objective in the outer loop, and Preconditioned Conjugate Gradient (PCG) to solve a sparse linear system in the inner loop. In this paper, we employ learnable optimizations to improve tracking robustness and speed up solver convergence. First, we upgrade the tracking objective by integrating an alignment data term on deep features which are learned end-to-end through CNN. The new tracking objective can capture the global deformation which helps Gauss-Newton to jump over local minimum, leading to robust tracking on large non-rigid motions. Second, we bridge the gap between the preconditioning technique and learning method by introducing a ConditionNet which is trained to generate a preconditioner such that PCG can converge within a small number of steps. Experimental results indicate that the proposed learning method converges faster than the original PCG by a large margin.

We propose ViewAL, a novel active learning strategy for semantic segmentation that exploits viewpoint consistency in multi-view datasets. Our core idea is that inconsistencies in model predictions across viewpoints provide a very reliable measure of uncertainty and encourage the model to perform well irrespective of the viewpoint under which objects are observed. To incorporate this uncertainty measure, we introduce a new viewpoint entropy formulation, which is the basis of our active learning strategy. In addition, we propose uncertainty computations on a superpixel level, which exploits inherently localized signal in the segmentation task, directly lowering the annotation costs. This combination of viewpoint entropy and the use of superpixels allows to efficiently select samples that are highly informative for improving the network. We demonstrate that our proposed active learning strategy not only yields the best-performing models for the same amount of required labeled data, but also significantly reduces labeling effort. For instance, our method achieves 95% of maximum achievable network performance using only 7%, 17%, and 24% labeled data on SceneNet-RGBD, ScanNet, and Matterport3D, respectively. On these datasets, the best state-of-the-art method achieves the same performance with 14%, 27% and 33% labeled data. Finally, we demonstrate that labeling using superpixels yields the same quality of ground-truth compared to labeling whole images, but requires 25% less time.

We introduce a novel, end-to-end learnable, differentiable non-rigid tracker that enables state-of-the-art non-rigid reconstruction by a learned robust optimization. Given two input RGB-D frames of a non-rigidly moving object, we employ a convolutional neural network to predict dense correspondences and their confidences. These correspondences are used as constraints in an as-rigid-as-possible (ARAP) optimization problem. By enabling gradient back-propagation through the weighted non-linear least squares solver, we are able to learn correspondences and confidences in an end-to-end manner such that they are optimal for the task of non-rigid tracking. Under this formulation, correspondence confidences can be learned via self-supervision, informing a learned robust optimization, where outliers and wrong correspondences are automatically down-weighted to enable effective tracking. Compared to state-of-the-art approaches, our algorithm shows improved reconstruction performance, while simultaneously achieving 85 times faster correspondence prediction than comparable deep-learning based methods.

Multi-view Stereo (MVS) is a common solution in photogrammetry applications for the dense reconstruction of a static scene from images. The static scene assumption, however, limits the general applicability of MVS algorithms, as many day-to-day scenes undergo non-rigid motion, e.g., clothes, faces, or human bodies. In this paper, we open up a new challenging direction: Dense 3D reconstruction of scenes with non-rigid changes observed from a small number of images sparsely captured from different views with a single monocular camera, which we call non-rigid multi-view stereo (NRMVS) problem. We formulate this problem as a joint optimization of deformation and depth estimation, using deformation graphs as the underlying representation. We propose a new sparse 3D to 2D matching technique with a dense patch-match evaluation scheme to estimate the most plausible deformation field satisfying depth and photometric consistency. We show that a dense reconstruction of a scene with non-rigid changes from a few images is possible, and demonstrate that our method can be used to interpolate novel deformed scenes from various combinations of deformation estimates derived from the sparse views.

Abstract Efficient rendering of photo‐realistic virtual worlds is a long standing effort of computer graphics. Modern graphics techniques have succeeded in synthesizing photo‐realistic images from hand‐crafted scene representations. However, the automatic generation of shape, materials, lighting, and other aspects of scenes remains a challenging problem that, if solved, would make photo‐realistic computer graphics more widely accessible. Concurrently, progress in computer vision and machine learning have given rise to a new approach to image synthesis and editing, namely deep generative models. Neural rendering is a new and rapidly emerging field that combines generative machine learning techniques with physical knowledge from computer graphics, e.g., by the integration of differentiable rendering into network training. With a plethora of applications in computer graphics and vision, neural rendering is poised to become a new area in the graphics community, yet no survey of this emerging field exists. This state‐of‐the‐art report summarizes the recent trends and applications of neural rendering. We focus on approaches that combine classic computer graphics techniques with deep generative models to obtain controllable and photorealistic outputs. Starting with an overview of the underlying computer graphics and machine learning concepts, we discuss critical aspects of neural rendering approaches. Specifically, our emphasis is on the type of control, i.e., how the control is provided, which parts of the pipeline are learned, explicit vs. implicit control, generalization, and stochastic vs. deterministic synthesis. The second half of this state‐of‐the‐art report is focused on the many important use cases for the described algorithms such as novel view synthesis, semantic photo manipulation, facial and body reenactment, relighting, free‐viewpoint video, and the creation of photo‐realistic avatars for virtual and augmented reality telepresence. Finally, we conclude with a discussion of the social implications of such technology and investigate open research problems.

We introduce a method for egocentric videoconferencing that enables hands-free video calls, for instance by people wearing smart glasses or other mixed-reality devices. Videoconferencing portrays valuable non-verbal communication and face expression cues, but usually requires a front-facing camera. Using a frontal camera in a hands-free setting when a person is on the move is impractical. Even holding a mobile phone camera in the front of the face while sitting for a long duration is not convenient. To overcome these issues, we propose a low-cost wearable egocentric camera setup that can be integrated into smart glasses. Our goal is to mimic a classical video call, and therefore, we transform the egocentric perspective of this camera into a front facing video. To this end, we employ a conditional generative adversarial neural network that learns a transition from the highly distorted egocentric views to frontal views common in videoconferencing. Our approach learns to transfer expression details directly from the egocentric view without using a complex intermediate parametric expressions model, as it is used by related face reenactment methods. We successfully handle subtle expressions, not easily captured by parametric blendshape-based solutions, e.g., tongue movement, eye movements, eye blinking, strong expressions and depth varying movements. To get control over the rigid head movements in the target view, we condition the generator on synthetic renderings of a moving neutral face. This allows us to synthesis results at different head poses. Our technique produces temporally smooth video-realistic renderings in real-time using a video-to-video translation network in conjunction with a temporal discriminator. We demonstrate the improved capabilities of our technique by comparing against related state-of-the art approaches.

We present Scan2CAD, a novel data-driven method that learns to align clean 3D CAD models from a shape database to the noisy and incomplete geometry of a commodity RGB-D scan. For a 3D reconstruction of an indoor scene, our method takes as input a set of CAD models, and predicts a 9DoF pose that aligns each model to the underlying scan geometry. To tackle this problem, we create a new scan-to-CAD alignment dataset based on 1506 ScanNet scans with 97607 annotated keypoint pairs between 14225 CAD models from ShapeNet and their counterpart objects in the scans. Our method selects a set of representative keypoints in a 3D scan for which we find correspondences to the CAD geometry. To this end, we design a novel 3D CNN architecture that learns a joint embedding between real and synthetic objects, and from this predicts a correspondence heatmap. Based on these correspondence heatmaps, we formulate a variational energy minimization that aligns a given set of CAD models to the reconstruction. We evaluate our approach on our newly introduced Scan2CAD benchmark where we outperform both handcrafted feature descriptor as well as state-of-the-art CNN based methods by 21.39%.

Modern computer vision algorithms have brought significant advancement to 3D geometry reconstruction. However, illumination and material reconstruction remain less studied, with current approaches assuming very simplified models for materials and illumination. We introduce Inverse Path Tracing, a novel approach to jointly estimate the material properties of objects and light sources in indoor scenes by using an invertible light transport simulation. We assume a coarse geometry scan, along with corresponding images and camera poses. The key contribution of this work is an accurate and simultaneous retrieval of light sources and physically based material properties (e.g., diffuse reflectance, specular reflectance, roughness, etc.) for the purpose of editing and re-rendering the scene under new conditions. To this end, we introduce a novel optimization method using a differentiable Monte Carlo renderer that computes derivatives with respect to the estimated unknown illumination and material properties. This enables joint optimization for physically correct light transport and material models using a tailored stochastic gradient descent.

We introduce Scan2Mesh, a novel data-driven generative approach which transforms an unstructured and potentially incomplete range scan into a structured 3D mesh representation. The main contribution of this work is a generative neural network architecture whose input is a range scan of a 3D object and whose output is an indexed face set conditioned on the input scan. In order to generate a 3D mesh as a set of vertices and face indices, the generative model builds on a series of proxy losses for vertices, edges, and faces. At each stage, we realize a one-to-one discrete mapping between the predicted and ground truth data points with a combination of convolutional- and graph neural network architectures. This enables our algorithm to predict a compact mesh representation similar to those created through manual artist effort using 3D modeling software. Our generated mesh results thus produce sharper, cleaner meshes with a fundamentally different structure from those generated through implicit functions, a first step in bridging the gap towards artist-created CAD models.

We introduce 3D-SIS, a novel neural network architecture for 3D semantic instance segmentation in commodity RGB-D scans. The core idea of our method to jointly learn from both geometric and color signal, thus enabling accurate instance predictions. Rather than operate solely on 2D frames, we observe that most computer vision applications have multi-view RGB-D input available, which we leverage to construct an approach for 3D instance segmentation that effectively fuses together these multi-modal inputs. Our network leverages high-resolution RGB input by associating 2D images with the volumetric grid based on the pose alignment of the 3D reconstruction. For each image, we first extract 2D features for each pixel with a series of 2D convolutions; we then backproject the resulting feature vector to the associated voxel in the 3D grid. This combination of 2D and 3D feature learning allows significantly higher accuracy object detection and instance segmentation than state-of-the-art alternatives. We show results on both synthetic and real-world public benchmarks, achieving an improvement in mAP of over 13 on real-world data.

We introduce, TextureNet, a neural network architecture designed to extract features from high-resolution signals associated with 3D surface meshes (e.g., color texture maps). The key idea is to utilize a 4-rotational symmetric(4-RoSy) field to define a domain for convolution on a surface. Though 4-RoSy fields have several properties favor-able for convolution on surfaces (low distortion, few singularities, consistent parameterization, etc.), orientations are ambiguous up to 4-fold rotation at any sample point. So, we introduce a new convolutional operator invariant to the4-RoSy ambiguity and use it in a network to extract features from high-resolution signals on geodesic neighborhoods of a surface. In comparison to alternatives, such as PointNet-based methods which lack a notion of orientation, the coherent structure given by these neighborhoods results in significantly stronger features. As an example application, we demonstrate the benefits of our architecture for 3D semantic segmentation of textured 3D meshes. The results show that our method outperforms all existing methods on the basis of mean IoU by a significant margin in both geometry-only(6.4%) and RGB+Geometry (6.9-8.2%) settings.

In this work, we address the lack of 3D understanding of generative neural networks by introducing a persistent 3D feature embedding for view synthesis. To this end, we propose DeepVoxels, a learned representation that encodes the view-dependent appearance of a 3D scene without having to explicitly model its geometry. At its core, our approach is based on a Cartesian 3D grid of persistent embedded features that learn to make use of the underlying 3D scene structure. Our approach combines insights from 3D geometric computer vision with recent advances in learning image-to-image mappings based on adversarial loss functions. DeepVoxels is supervised, without requiring a 3D reconstruction of the scene, using a 2D re-rendering loss and enforces perspective and multi-view geometry in a principled manner. We apply our persistent 3D scene representation to the problem of novel view synthesis demonstrating high-quality results for a variety of challenging scenes.

We present a novel, end-to-end approach to align CAD models to an 3D scan of a scene, enabling transformation of a noisy, incomplete 3D scan to a compact, CAD reconstruction with clean, complete object geometry. Our main contribution lies in formulating a differentiable Procrustes alignment that is paired with a symmetry-aware dense object correspondence prediction. To simultaneously align CAD models to all the objects of a scanned scene, our approach detects object locations, then predicts symmetry-aware dense object correspondences between scan and CAD geometry in a unified object space, as well as a nearest neighbor CAD model, both of which are then used to inform a differentiable Procrustes alignment. Our approach operates in a fully-convolutional fashion, enabling alignment of CAD models to the objects of a scan in a single forward pass. This enables our method to outperform state-of-the-art approaches by 19.04% for CAD model alignment to scans, with approximately ≈250x faster runtime than previous data-driven approaches.

3D scan geometry and CAD models often contain complementary information towards understanding environments, which could be leveraged through establishing a mapping between the two domains. However, this is a challenging task due to strong, lower-level differences between scan and CAD geometry. We propose a novel approach to learn a joint embedding space between scan and CAD geometry, where semantically similar objects from both domains lie close together. To achieve this, we introduce a new 3D CNN-based approach to learn a joint embedding space representing object similarities across these domains. To learn a shared space where scan objects and CAD models can interlace, we propose a stacked hourglass approach to separate foreground and background from a scan object, and transform it to a complete, CAD-like representation to produce a shared embedding space. This embedding space can then be used for CAD model retrieval; to further enable this task, we introduce a new dataset of ranked scan-CAD similarity annotations, enabling new, fine-grained evaluation of CAD model retrieval to cluttered, noisy, partial scans. Our learned joint embedding outperforms current state of the art for CAD model retrieval by 12% in instance retrieval accuracy.

We present a Deep Differentiable Simplex Layer (DDSL) for neural networks for geometric deep learning. The DDSL is a differentiable layer compatible with deep neural networks for bridging simplex mesh-based geometry representations (point clouds, line mesh, triangular mesh, tetrahedral mesh) with raster images (e.g., 2D/3D grids). The DDSL uses Non-Uniform Fourier Transform (NUFT) to perform differentiable, efficient, anti- aliased rasterization of simplex-based signals. We present a complete theoretical framework for the process as well as an efficient backpropagation algorithm. Compared to previous differentiable renderers and rasterizers, the DDSL generalizes to arbitrary simplex degrees and dimensions. In particular, we explore its applications to 2D shapes and illustrate two applications of this method: (1) mesh editing and optimization guided by neural network outputs, and (2) using DDSL for a differentiable rasterization loss to facilitate end-to-end training of polygon generators. We are able to validate the effectiveness of gradient-based shape optimization with the example of airfoil optimization, and using the differentiable rasterization loss to facilitate end-to-end training, we surpass state of the art for polygonal image segmentation given ground-truth bounding boxes.

The rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns for the implications towards society. At best, this leads to a loss of trust in digital content, but could potentially cause further harm by spreading false information or fake news. This paper examines the realism of state-of-the-art image manipulations, and how difficult it is to detect them, either automatically or by humans. To standardize the evaluation of detection methods, we propose an automated benchmark for facial manipulation detection. In particular, the benchmark is based on Deep-Fakes, Face2Face, FaceSwap and NeuralTextures as prominent representatives for facial manipulations at random compression level and size. The benchmark is publicly available and contains a hidden test set as well as a database of over 1.8 million manipulated images. This dataset is over an order of magnitude larger than comparable, publicly available, forgery datasets. Based on this data, we performed a thorough analysis of data-driven forgery detectors. We show that the use of additional domain-specific knowledge improves forgery detection to unprecedented accuracy, even in the presence of strong compression, and clearly outperforms human observers.

In this work, we introduce the task of 3D object instance re-localization (RIO): given one or multiple objects in an RGB-D scan, we want to estimate their corresponding 6DoF poses in another 3D scan of the same environment taken at a later point in time. We consider RIO a particularly important task in 3D vision since it enables a wide range of practical applications, including AI-assistants or robots that are asked to find a specific object in a 3D scene. To address this problem, we first introduce 3RScan, a novel dataset and benchmark, which features 1482 RGB-D scans of 478 environments across multiple time steps. Each scene includes several objects whose positions change over time, together with ground truth annotations of object instances and their respective 6DoF mappings among re-scans. Automatically finding 6DoF object poses leads to a particular challenging feature matching task due to varying partial observations and changes in the surrounding context. To this end, we introduce a new data-driven approach that efficiently finds matching features using a fully-convolutional 3D correspondence network operating on multiple spatial scales. Combined with a 6DoF pose optimization, our method outperforms state-of-the-art baselines on our newly-established benchmark, achieving an accuracy of 30.58%.

Abstract We propose a novel approach to robot‐operated active understanding of unknown indoor scenes, based on online RGBD reconstruction with semantic segmentation. In our method, the exploratory robot scanning is both driven by and targeting at the recognition and segmentation of semantic objects from the scene. Our algorithm is built on top of a volumetric depth fusion framework and performs real‐time voxel‐based semantic labeling over the online reconstructed volume. The robot is guided by an online estimated discrete viewing score field (VSF) parameterized over the 3D space of 2D location and azimuth rotation. VSF stores for each grid the score of the corresponding view, which measures how much it reduces the uncertainty (entropy) of both geometric reconstruction and semantic labeling. Based on VSF, we select the next best views (NBV) as the target for each time step. We then jointly optimize the traverse path and camera trajectory between two adjacent NBVs, through maximizing the integral viewing score (information gain) along path and trajectory. Through extensive evaluation, we show that our method achieves efficient and accurate online scene parsing during exploratory scanning.

We present an autonomous scanning approach which allows multiple robots to perform collaborative scanning for dense 3D reconstruction of unknown indoor scenes. Our method plans scanning paths for several robots, allowing them to efficiently coordinate with each other such that the collective scanning coverage and reconstruction quality is maximized while the overall scanning effort is minimized. To this end, we define the problem as a dynamic task assignment and introduce a novel formulation based on Optimal Mass Transport (OMT). Given the currently scanned scene, a set of task views are extracted to cover scene regions which are either unknown or uncertain. These task views are assigned to the robots based on the OMT optimization. We then compute for each robot a smooth path over its assigned tasks by solving an approximate traveling salesman problem. In order to showcase our algorithm, we implement a multi-robot auto-scanning system. Since our method is computationally efficient, we can easily run it in real time on commodity hardware, and combine it with online RGB-D reconstruction approaches. In our results, we show several real-world examples of large indoor environments; in addition, we build a benchmark with a series of carefully designed metrics for quantitatively evaluating multi-robot autoscanning. Overall, we are able to demonstrate high-quality scanning results with respect to reconstruction quality and scanning efficiency, which significantly outperforms existing multi-robot exploration systems.

We introduce a new method that efficiently computes a set of viewpoints and trajectories for high-quality 3D reconstructions in outdoor environments. Our goal is to automatically explore an unknown area and obtain a complete 3D scan of a region of interest (e.g., a large building). Images from a commodity RGB camera, mounted on an autonomously navigated quadcopter, are fed into a multi-view stereo reconstruction pipeline that produces high-quality results but is computationally expensive. In this setting, the scanning result is constrained by the restricted flight time of quadcopters. To this end, we introduce a novel optimization strategy that respects these constraints by maximizing the information gain from sparsely sampled viewpoints while limiting the total travel distance of the quadcopter. At the core of our method lies a hierarchical volumetric representation that allows the algorithm to distinguish between unknown, free, and occupied space. Furthermore, our information gain-based formulation leverages this representation to handle occlusions in an efficient manner. In addition to the surface geometry, we utilize free-space information to avoid obstacles and determine collision-free flight paths. Our tool can be used to specify the region of interest and to plan trajectories. We demonstrate our method by obtaining a number of compelling 3D reconstructions, and we provide a thorough quantitative evaluation showing improvement over previous state-of-the-art and regular patterns.

The modern computer graphics pipeline can synthesize images at remarkable visual quality; however, it requires well-defined, high-quality 3D content as input. In this work, we explore the use of imperfect 3D content, for instance, obtained from photo-metric reconstructions with noisy and incomplete surface geometry, while still aiming to produce photo-realistic (re-)renderings. To address this challenging problem, we introduce Deferred Neural Rendering , a new paradigm for image synthesis that combines the traditional graphics pipeline with learnable components. Specifically, we propose Neural Textures , which are learned feature maps that are trained as part of the scene capture process. Similar to traditional textures, neural textures are stored as maps on top of 3D mesh proxies; however, the high-dimensional feature maps contain significantly more information, which can be interpreted by our new deferred neural rendering pipeline. Both neural textures and deferred neural renderer are trained end-to-end, enabling us to synthesize photo-realistic images even when the original 3D content was imperfect. In contrast to traditional, black-box 2D generative neural networks, our 3D representation gives us explicit control over the generated output, and allows for a wide range of application domains. For instance, we can synthesize temporally-consistent video re-renderings of recorded 3D scenes as our representation is inherently embedded in 3D space. This way, neural textures can be utilized to coherently re-render or manipulate existing video content in both static and dynamic environments at real-time rates. We show the effectiveness of our approach in several experiments on novel view synthesis, scene editing, and facial reenactment, and compare to state-of-the-art approaches that leverage the standard graphics pipeline as well as conventional generative neural networks.

Real-life man-made objects often exhibit strong and easily-identifiable structure, as a direct result of their design or their intended functionality. Structure typically appears in the form of individual parts and their arrangement. Knowing about object structure can be an important cue for object recognition and scene understanding - a key goal for various AR and robotics applications. However, commodity RGB-D sensors used in these scenarios only produce raw, unorganized point clouds, without structural information about the captured scene. Moreover, the generated data is commonly partial and susceptible to artifacts and noise, which makes inferring the structure of scanned objects challenging. In this paper, we organize large shape collections into parameterized shape templates to capture the underlying structure of the objects. The templates allow us to transfer the structural information onto new objects and incomplete scans. We employ a deep neural network that matches the partial scan with one of the shape templates, then match and fit it to complete and detailed models from the collection. This allows us to faithfully label its parts and to guide the reconstruction of the scanned object. We showcase the effectiveness of our method by comparing it to other state-of-the-art approaches.

We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels. The key contribution of our method is its ability to handle large scenes with varying spatial extent, managing the cubic growth in data size as scene size increases. To this end, we devise a fully-convolutional generative 3D CNN model whose filter kernels are invariant to the overall scene size. The model can be trained on scene subvolumes but deployed on arbitrarily large scenes at test time. In addition, we propose a coarse-to-fine inference strategy in order to produce high-resolution output while also leveraging large input context sizes. In an extensive series of experiments, we carefully evaluate different model design choices, considering both deterministic and probabilistic models for completion and semantic inference. Our results show that we outperform other methods not only in the size of the environments handled and processing efficiency, but also with regard to completion quality and semantic segmentation performance by a significant margin.

Abstract QuadriFlow is a scalable algorithm for generating quadrilateral surface meshes based on the Instant Field‐Aligned Meshes of Jakob et al. (ACM Trans. Graph. 34(6):189, 2015). We modify the original algorithm such that it efficiently produces meshes with many fewer singularities. Singularities in quadrilateral meshes cause problems for many applications, including parametrization and rendering with Catmull‐Clark subdivision surfaces. Singularities can rarely be entirely eliminated, but it is possible to keep their number small. Local optimization algorithms usually produce meshes with many singularities, whereas the best algorithms tend to require non‐local optimization, and therefore are slow. We propose an efficient method to minimize singularities by combining the Instant Meshes objective with a system of linear and quadratic constraints. These constraints are enforced by solving a global minimum‐cost network flow problem and local boolean satisfiability problems. We have verified the robustness and efficiency of our method on a subset of ShapeNet comprising 17,791 3D objects in the wild. Our evaluation shows that the quality of the quadrangulations generated by our method is as good as, if not better than, those from other methods, achieving about four times fewer singularities than Instant Meshes. Other algorithms that produce similarly few singularities are much slower; we take less than ten seconds to process each model. Our source code is publicly available.

Abstract The advent of affordable consumer grade RGB‐D cameras has brought about a profound advancement of visual scene reconstruction methods. Both computer graphics and computer vision researchers spend significant effort to develop entirely new algorithms to capture comprehensive shape models of static and dynamic scenes with RGB‐D cameras. This led to significant advances of the state of the art along several dimensions. Some methods achieve very high reconstruction detail, despite limited sensor resolution. Others even achieve real‐time performance, yet possibly at lower quality. New concepts were developed to capture scenes at larger spatial and temporal extent. Other recent algorithms flank shape reconstruction with concurrent material and lighting estimation, even in general scenes and unconstrained conditions. In this state‐of‐the‐art report, we analyze these recent developments in RGB‐D scene reconstruction in detail and review essential related work. We explain, compare, and critically analyze the common underlying algorithmic concepts that enabled these recent advancements. Furthermore, we show how algorithms are designed to best exploit the benefits of RGB‐D data while suppressing their often non‐trivial data distortions. In addition, this report identifies and discusses important open research questions and suggests relevant directions for future work.

Abstract The computer graphics and vision communities have dedicated long standing efforts in building computerized tools for reconstructing, tracking, and analyzing human faces based on visual input. Over the past years rapid progress has been made, which led to novel and powerful algorithms that obtain impressive results even in the very challenging case of reconstruction from a single RGB or RGB‐D camera. The range of applications is vast and steadily growing as these technologies are further improving in speed, accuracy, and ease of use. Motivated by this rapid progress, this state‐of‐the‐art report summarizes recent trends in monocular facial performance capture and discusses its applications, which range from performance‐based animation to real‐time facial reenactment. We focus our discussion on methods where the central task is to recover and track a three dimensional model of the human face using optimization‐based reconstruction algorithms. We provide an in‐depth overview of the underlying concepts of real‐world image formation, and we discuss common assumptions and simplifications that make these algorithms practical. In addition, we extensively cover the priors that are used to better constrain the under‐constrained monocular reconstruction problem, and discuss the optimization techniques that are employed to recover dense, photo‐geometric 3D face models from monocular 2D data. Finally, we discuss a variety of use cases for the reviewed algorithms in the context of motion capture, facial animation, as well as image and video editing.

We present a novel approach that enables photo-realistic re-animation of portrait videos using only an input video. In contrast to existing approaches that are restricted to manipulations of facial expressions only, we are the first to transfer the full 3D head position, head rotation, face expression, eye gaze, and eye blinking from a source actor to a portrait video of a target actor. The core of our approach is a generative neural network with a novel space-time architecture. The network takes as input synthetic renderings of a parametric face model, based on which it predicts photo-realistic video frames for a given target actor. The realism in this rendering-to-video transfer is achieved by careful adversarial training, and as a result, we can create modified target videos that mimic the behavior of the synthetically-created input. In order to enable source-to-target video re-animation, we render a synthetic target video with the reconstructed head animation parameters from a source video, and feed it into the trained network - thus taking full control of the target. With the ability to freely recombine source and target parameters, we are able to demonstrate a large variety of video rewrite applications without explicitly modeling hair, body or background. For instance, we can reenact the full head using interactive user-controlled editing, and realize high-fidelity visual dubbing. To demonstrate the high quality of our output, we conduct an extensive series of experiments and evaluations, where for instance a user study shows that our video edits are hard to detect.

We propose FaceVR , a novel image-based method that enables video teleconferencing in VR based on self-reenactment. State-of-the-art face tracking methods in the VR context are focused on the animation of rigged 3D avatars (Li et al. 2015; Olszewski et al. 2016). Although they achieve good tracking performance, the results look cartoonish and not real. In contrast to these model-based approaches, FaceVR enables VR teleconferencing using an image-based technique that results in nearly photo-realistic outputs. The key component of FaceVR is a robust algorithm to perform real-time facial motion capture of an actor who is wearing a head-mounted display (HMD), as well as a new data-driven approach for eye tracking from monocular videos. Based on reenactment of a prerecorded stereo video of the person without the HMD, FaceVR incorporates photo-realistic re-rendering in real time, thus allowing artificial modifications of face and eye appearances. For instance, we can alter facial expressions or change gaze directions in the prerecorded target video. In a live setup, we apply these newly introduced algorithmic components.

We propose HeadOn, the first real-time source-to-target reenactment approach for complete human portrait videos that enables transfer of torso and head motion, face expression, and eye gaze. Given a short RGB-D video of the target actor, we automatically construct a personalized geometry proxy that embeds a parametric head, eye, and kinematic torso model. A novel realtime reenactment algorithm employs this proxy to photo-realistically map the captured motion from the source actor to the target actor. On top of the coarse geometric proxy, we propose a video-based rendering technique that composites the modified target portrait video via view- and pose-dependent texturing, and creates photo-realistic imagery of the target actor under novel torso and head poses, facial expressions, and gaze directions. To this end, we propose a robust tracking of the face and torso of the source actor. We extensively evaluate our approach and show significant improvements in enabling much greater flexibility in creating realistic reenacted output videos.

Access to large, diverse RGB-D datasets is critical for training RGB-D scene understanding algorithms. However, existing datasets still cover only a limited number of views or a restricted scale of spaces. In this paper, we introduce Matterport3D, a large-scale RGB-D dataset containing 10,800 panoramic views from 194,400 RGB-D images of 90 building-scale scenes. Annotations are provided with surface reconstructions, camera poses, and 2D and 3D semantic segmentations. The precise global alignment and comprehensive, diverse panoramic set of views over entire buildings enable a variety of supervised and self-supervised computer vision tasks, including keypoint matching, view overlap prediction, normal prediction from color, semantic segmentation, and region classification.

We introduce a novel multiframe scene flow approach that jointly optimizes the consistency of the patch appearances and their local rigid motions from RGB-D image sequences. In contrast to the competing methods, we take advantage of an oversegmentation of the reference frame and robust optimization techniques. We formulate scene flow recovery as a global non-linear least squares problem which is iteratively solved by a damped Gauss-Newton approach. As a result, we obtain a qualitatively new level of accuracy in RGB-D based scene flow estimation which can potentially run in real-time. Our method can handle challenging cases with rigid, piecewise rigid, articulated and moderate non-rigid motion, and does not rely on prior knowledge about the types of motions and deformations. Extensive experiments on synthetic and real data show that our method outperforms state-of-the-art.

A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very little data is available - current datasets cover a small range of scene views and have limited semantic annotations. To address this issue, we introduce ScanNet, an RGB-D video dataset containing 2.5M views in 1513 scenes annotated with 3D camera poses, surface reconstructions, and semantic segmentations. To collect this data, we designed an easy-to-use and scalable RGB-D capture system that includes automated surface reconstruction and crowd-sourced semantic annotation.We show that using this data helps achieve state-of-the-art performance on several 3D scene understanding tasks, including 3D object classification, semantic voxel labeling, and CAD model retrieval.

We introduce a data-driven approach to complete partial 3D shapes through a combination of volumetric deep neural networks and 3D shape synthesis. From a partially-scanned input shape, our method first infers a low-resolution – but complete – output. To this end, we introduce a 3D-Encoder-Predictor Network (3D-EPN) which is composed of 3D convolutional layers. The network is trained to predict and fill in missing data, and operates on an implicit surface representation that encodes both known and unknown space. This allows us to predict global structure in unknown areas at high accuracy. We then correlate these intermediary results with 3D geometry from a shape database at test time. In a final pass, we propose a patch-based 3D shape synthesis method that imposes the 3D geometry from these retrieved shapes as constraints on the coarsely-completed mesh. This synthesis process enables us to reconstruct fine-scale detail and generate high-resolution output while respecting the global mesh structure obtained by the 3D-EPN. Although our 3D-EPN outperforms state-of-the-art completion method, the main contribution in our work lies in the combination of a data-driven shape predictor and analytic 3D shape synthesis. In our results, we show extensive evaluations on a newly-introduced shape completion benchmark for both real-world and synthetic data.

Matching local geometric features on real-world depth images is a challenging task due to the noisy, low-resolution, and incomplete nature of 3D scan data. These difficulties limit the performance of current state-of-art methods, which are typically based on histograms over geometric properties. In this paper, we present 3DMatch, a data-driven model that learns a local volumetric patch descriptor for establishing correspondences between partial 3D data. To amass training data for our model, we propose a self-supervised feature learning method that leverages the millions of correspondence labels found in existing RGB-D reconstructions. Experiments show that our descriptor is not only able to match local geometry in new scenes for reconstruction, but also generalize to different tasks and spatial scales (e.g. instance-level object model alignment for the Amazon Picking Challenge, and mesh surface correspondence). Results show that 3DMatch consistently outperforms other state-of-the-art approaches by a significant margin. Code, data, benchmarks, and pre-trained models are available online at http://3dmatch.cs.princeton.edu.

Estimating surface reflectance (BRDF) is one key component for complete 3D scene capture, with wide applications in virtual reality, augmented reality, and human computer interaction. Prior work is either limited to controlled environments (e.g., gonioreflectometers, light stages, or multi-camera domes), or requires the joint optimization of shape, illumination, and reflectance, which is often computationally too expensive (e.g., hours of running time) for real-time applications. Moreover, most prior work requires HDR images as input which further complicates the capture process. In this paper, we propose a lightweight approach for surface reflectance estimation directly from 8-bit RGB images in real-time, which can be easily plugged into any 3D scanning-and-fusion system with a commodity RGBD sensor. Our method is learning-based, with an inference time of less than 90ms per scene and a model size of less than 340K bytes. We propose two novel network architectures, HemiCNN and Grouplet, to deal with the unstructured input data from multiple viewpoints under unknown illumination. We further design a loss function to resolve the color-constancy and scale ambiguity. In addition, we have created a large synthetic dataset, SynBRDF, which comprises a total of 500K RGBD images rendered with a physically-based ray tracer under a variety of natural illumination, covering 5000 materials and 5000 shapes. SynBRDF is the first large-scale benchmark dataset for reflectance estimation. Experiments on both synthetic data and real data show that the proposed method effectively recovers surface reflectance, and outperforms prior work for reflectance estimation in uncontrolled environments.

We introduce a novel method to obtain high-quality 3D reconstructions from consumer RGB-D sensors. Our core idea is to simultaneously optimize for geometry encoded in a signed distance field (SDF), textures from automatically-selected keyframes, and their camera poses along with material and scene lighting. To this end, we propose a joint surface reconstruction approach that is based on Shape-from-Shading (SfS) techniques and utilizes the estimation of spatially-varying spherical harmonics (SVSH) from subvolumes of the reconstructed scene. Through extensive examples and evaluations, we demonstrate that our method dramatically increases the level of detail in the reconstructed scene geometry and contributes highly to consistent surface texture recovery.

Autonomous reconstruction of unknown scenes by a mobile robot inherently poses the question of balancing between exploration efficacy and reconstruction quality. We present a navigation-by-reconstruction approach to address this question, where moving paths of the robot are planned to account for both global efficiency for fast exploration and local smoothness to obtain high-quality scans. An RGB-D camera, attached to the robot arm, is dictated by the desired reconstruction quality as well as the movement of the robot itself. Our key idea is to harness a time-varying tensor field to guide robot movement, and then solve for 3D camera control under the constraint of the 2D robot moving path. The tensor field is updated in real time, conforming to the progressively reconstructed scene. We show that tensor fields are well suited for guiding autonomous scanning for two reasons: first, they contain sparse and controllable singularities that allow generating a locally smooth robot path, and second, their topological structure can be used for globally efficient path routing within a partially reconstructed scene. We have conducted numerous tests with a mobile robot, and demonstrate that our method leads to a smooth exploration and high-quality reconstruction of unknown indoor scenes.

Real-time, high-quality, 3D scanning of large-scale scenes is key to mixed reality and robotic applications. However, scalability brings challenges of drift in pose estimation, introducing significant errors in the accumulated model. Approaches often require hours of offline processing to globally correct model errors. Recent online methods demonstrate compelling results but suffer from (1) needing minutes to perform online correction, preventing true real-time use; (2) brittle frame-to-frame (or frame-to-model) pose estimation, resulting in many tracking failures; or (3) supporting only unstructured point-based representations, which limit scan quality and applicability. We systematically address these issues with a novel, real-time, end-to-end reconstruction framework. At its core is a robust pose estimation strategy, optimizing per frame for a global set of camera poses by considering the complete history of RGB-D input with an efficient hierarchical approach. We remove the heavy reliance on temporal tracking and continually localize to the globally optimized frames instead. We contribute a parallelizable optimization framework, which employs correspondences based on sparse features and dense geometric and photometric matching. Our approach estimates globally optimized (i.e., bundle adjusted) poses in real time, supports robust tracking with recovery from gross tracking failures (i.e., relocalization), and re-estimates the 3D model in real time to ensure global consistency, all within a single framework. Our approach outperforms state-of-the-art online systems with quality on par to offline methods, but with unprecedented speed and scan completeness. Our framework leads to a comprehensive online scanning solution for large indoor environments, enabling ease of use and high-quality results. 1

Many graphics and vision problems can be expressed as non-linear least squares optimizations of objective functions over visual data, such as images and meshes. The mathematical descriptions of these functions are extremely concise, but their implementation in real code is tedious, especially when optimized for real-time performance on modern GPUs in interactive applications. In this work, we propose a new language, Opt, 1 for writing these objective functions over image- or graph-structured unknowns concisely and at a high level. Our compiler automatically transforms these specifications into state-of-the-art GPU solvers based on Gauss-Newton or Levenberg-Marquardt methods. Opt can generate different variations of the solver, so users can easily explore tradeoffs in numerical precision, matrix-free methods, and solver approaches. In our results, we implement a variety of real-world graphics and vision applications. Their energy functions are expressible in tens of lines of code and produce highly optimized GPU solver implementations. These solvers are competitive in performance with the best published hand-tuned, application-specific GPU solvers, and orders of magnitude beyond a general-purpose auto-generated solver.

We present 3DLite 1 , a novel approach to reconstruct 3D environments using consumer RGB-D sensors, making a step towards directly utilizing captured 3D content in graphics applications, such as video games, VR, or AR. Rather than reconstructing an accurate one-to-one representation of the real world, our method computes a lightweight, low-polygonal geometric abstraction of the scanned geometry. We argue that for many graphics applications it is much more important to obtain high-quality surface textures rather than highly-detailed geometry. To this end, we compensate for motion blur, auto-exposure artifacts, and micro-misalignments in camera poses by warping and stitching image fragments from low-quality RGB input data to achieve high-resolution, sharp surface textures. In addition to the observed regions of a scene, we extrapolate the scene geometry, as well as the mapped surface textures, to obtain a complete 3D model of the environment. We show that a simple planar abstraction of the scene geometry is ideally suited for this completion task, enabling 3DLite to produce complete, lightweight, and visually compelling 3D scene models. We believe that these CAD-like reconstructions are an important step towards leveraging RGB-D scanning in actual content creation pipelines.

In this paper, we present a novel, general, and efficient architecture for addressing computer vision problems that are approached from an 'Analysis by Synthesis' standpoint. Analysis by synthesis involves the minimization of reconstruction error, which is typically a non-convex function of the latent target variables. State-of-the-art methods adopt a hybrid scheme where discriminatively trained predictors like Random Forests or Convolutional Neural Networks are used to initialize local search algorithms. While these hybrid methods have been shown to produce promising results, they often get stuck in local optima. Our method goes beyond the conventional hybrid architecture by not only proposing multiple accurate initial solutions but by also defining a navigational structure over the solution space that can be used for extremely efficient gradient-free local search. We demonstrate the efficacy and generalizability of our approach on tasks as diverse as Hand Pose Estimation, RGB Camera Relocalization, and Image Retrieval.

3D shape models are becoming widely available and easier to capture, making available 3D information crucial for progress in object classification. Current state-of-theart methods rely on CNNs to address this problem. Recently, we witness two types of CNNs being developed: CNNs based upon volumetric representations versus CNNs based upon multi-view representations. Empirical results from these two types of CNNs exhibit a large gap, indicating that existing volumetric CNN architectures and approaches are unable to fully exploit the power of 3D representations. In this paper, we aim to improve both volumetric CNNs and multi-view CNNs according to extensive analysis of existing approaches. To this end, we introduce two distinct network architectures of volumetric CNNs. In addition, we examine multi-view CNNs, where we introduce multiresolution filtering in 3D. Overall, we are able to outperform current state-of-the-art methods for both volumetric CNNs and multi-view CNNs. We provide extensive experiments designed to evaluate underlying design choices, thus providing a better understanding of the space of methods available for object classification on 3D data.

We present a novel approach for real-time facial reenactment of a monocular target video sequence (e.g., Youtube video). The source sequence is also a monocular video stream, captured live with a commodity webcam. Our goal is to animate the facial expressions of the target video by a source actor and re-render the manipulated output video in a photo-realistic fashion. To this end, we first address the under-constrained problem of facial identity recovery from monocular video by non-rigid model-based bundling. At run time, we track facial expressions of both source and target video using a dense photometric consistency measure. Reenactment is then achieved by fast and efficient deformation transfer between source and target. The mouth interior that best matches the re-targeted expression is retrieved from the target sequence and warped to produce an accurate fit. Finally, we convincingly re-render the synthesized target face on top of the corresponding video stream such that it seamlessly blends with the real-world illumination. We demonstrate our method in a live setup, where Youtube videos are reenacted in real time.

Abstract Graphics hardware has progressively been optimized to render more triangles with increasingly flexible shading. For highly detailed geometry, interactive applications restricted themselves to performing transforms on fixed geometry, since they could not incur the cost required to generate and transfer smooth or displaced geometry to the GPU at render time. As a result of recent advances in graphics hardware, in particular the GPU tessellation unit, complex geometry can now be generated on the fly within the GPU's rendering pipeline. This has enabled the generation and displacement of smooth parametric surfaces in real‐time applications. However, many well‐established approaches in offline rendering are not directly transferable due to the limited tessellation patterns or the parallel execution model of the tessellation stage. In this survey, we provide an overview of recent work and challenges in this topic by summarizing, discussing, and comparing methods for the rendering of smooth and highly detailed surfaces in real time.

We present a novel method for real-time rendering of subdivision surfaces whose goal is to make subdivision faces as easy to render as triangles, points, or lines. Our approach uses standard GPU tessellation hardware and processes each face of a base mesh independently, thus allowing an entire model to be rendered in a single pass. The key idea of our method is to subdivide the u, v domain of each face ahead of time, generating a quadtree structure, and then submit one tessellated primitive per input face. By traversing the quadtree for each post-tessellation vertex, we are able to accurately and efficiently evaluate the limit surface. Our method yields a more uniform tessellation of the surface, and faster rendering, as fewer primitives are submitted. We evaluate our method on a variety of assets, and realize performance that can be three times faster than state-of-the-art approaches. In addition, our streaming formulation makes it easier to integrate subdivision surfaces into applications and shader code written for polygonal models. We illustrate integration of our technique into a full-featured video game engine.

We learn a probabilistic model connecting human poses and arrangements of object geometry from real-world observations of interactions collected with commodity RGB-D sensors. This model is encoded as a set of prototypical interaction graphs (PiGraphs), a human-centric representation capturing physical contact and visual attention linkages between 3D geometry and human body parts. We use this encoding of the joint probability distribution over pose and geometry during everyday interactions to generate interaction snapshots , which are static depictions of human poses and relevant objects during human-object interactions. We demonstrate that our model enables a novel human-centric understanding of 3D content and allows for jointly generating 3D scenes and interaction poses given terse high-level specifications, natural language, or reconstructed real-world scene constraints.

Computational photography systems are becoming increasingly diverse, while computational resources---for example on mobile platforms---are rapidly increasing. As diverse as these camera systems may be, slightly different variants of the underlying image processing tasks, such as demosaicking, deconvolution, denoising, inpainting, image fusion, and alignment, are shared between all of these systems. Formal optimization methods have recently been demonstrated to achieve state-of-the-art quality for many of these applications. Unfortunately, different combinations of natural image priors and optimization algorithms may be optimal for different problems, and implementing and testing each combination is currently a time-consuming and error-prone process. ProxImaL is a domain-specific language and compiler for image optimization problems that makes it easy to experiment with different problem formulations and algorithm choices. The language uses proximal operators as the fundamental building blocks of a variety of linear and nonlinear image formation models and cost functions, advanced image priors, and noise models. The compiler intelligently chooses the best way to translate a problem formulation and choice of optimization algorithm into an efficient solver implementation. In applications to the image processing pipeline, deconvolution in the presence of Poisson-distributed shot noise, and burst denoising, we show that a few lines of ProxImaL code can generate highly efficient solvers that achieve state-of-the-art results. We also show applications to the nonlinear and nonconvex problem of phase retrieval.

We present an augmented reality system for large scale 3D reconstruction and recognition in outdoor scenes. Unlike existing prior work, which tries to reconstruct scenes using active depth cameras, we use a purely passive stereo setup, allowing for outdoor use and extended sensing range. Our system not only produces a map of the 3D environment in real-time, it also allows the user to draw (or 'paint') with a laser pointer directly onto the reconstruction to segment the model into objects. Given these examples our system then learns to segment other parts of the 3D map during online acquisition. Unlike typical object recognition systems, ours therefore very much places the user 'in the loop' to segment particular objects of interest, rather than learning from predefined databases. The laser pointer additionally helps to 'clean up' the stereo reconstruction and final 3D map, interactively. Using our system, within minutes, a user can capture a full 3D map, segment it into objects of interest, and refine parts of the model during capture. We provide full technical details of our system to aid replication, as well as quantitative evaluation of system components. We demonstrate the possibility of using our system for helping the visually impaired navigate through spaces. Beyond this use, our system can be used for playing large-scale augmented reality games, shared online to augment streetview data, and used for more detailed car and person navigation.

Recent advances in camera relocalization use predictions from a regression forest to guide the camera pose optimization procedure. In these methods, each tree associates one pixel with a point in the scene's 3D world coordinate frame. In previous work, these predictions were point estimates and the subsequent camera pose optimization implicitly assumed an isotropic distribution of these estimates. In this paper, we train a regression forest to predict mixtures of anisotropic 3D Gaussians and show how the predicted uncertainties can be taken into account for continuous pose optimization. Experiments show that our proposed method is able to relocalize up to 40% more frames than the state of the art.

Our abilities in scene understanding, which allow us to perceive the 3D structure of our surroundings and intuitively recognise the objects we see, are things that we largely take for granted, but for robots, the task of understanding large scenes quickly remains extremely challenging. Recently, scene understanding approaches based on 3D reconstruction and semantic segmentation have become popular, but existing methods either do not scale, fail outdoors, provide only sparse reconstructions or are rather slow. In this paper, we build on a recent hash-based technique for large-scale fusion and an efficient mean-field inference algorithm for densely-connected CRFs to present what to our knowledge is the first system that can perform dense, large-scale, outdoor semantic reconstruction of a scene in (near) real time. We also present a `semantic fusion' approach that allows us to handle dynamic objects more effectively than previous approaches. We demonstrate the effectiveness of our approach on the KITTI dataset, and provide qualitative and quantitative results showing high-quality dense reconstruction and labelling of a number of scenes.

Feature-adaptive subdivision (FAS) is one of the state-of-the art real-time rendering methods for subdivision surfaces on modern GPUs. It enables efficient and accurate rendering of subdivision surfaces in many interactive applications, such as video games or authoring tools. In this paper, we present dynamic feature-adaptive subdivision (DFAS), which improves upon FAS by enabling an independent subdivision depth for every irregularity. Our subdivision kernels fill a dynamic patch buffer on-the-fly with the appropriate number of patches corresponding to the chosen level-of-detail scheme. By reducing the number of generated and processed patches, DFAS significantly improves upon the performance of static FAS.

Abstract In recent years, real‐time 3D scanning technology has developed significantly and is now able to capture large environments with considerable accuracy. Unfortunately, the reconstructed geometry still suffers from incompleteness, due to occlusions and lack of view coverage, resulting in unsatisfactory reconstructions. In order to overcome these fundamental physical limitations, we present a novel reconstruction approach based on retrieving objects from a 3D shape database while scanning an environment in real‐time. With this approach, we are able to replace scanned RGB‐D data with complete, hand‐modeled objects from shape databases. We align and scale retrieved models to the input data to obtain a high‐quality virtual representation of the real‐world environment that is quite faithful to the original geometry. In contrast to previous methods, we are able to retrieve objects in cluttered and noisy scenes even when the database contains only similar models, but no exact matches. In addition, we put a strong focus on object retrieval in an interactive scanning context — our algorithm runs directly on 3D scanning data structures, and is able to query databases of thousands of models in an online fashion during scanning.

Abstract We present a novel method to adaptively apply modifications to scene data stored in GPU memory. Such modifications may include interactive painting and sculpting operations in an authoring tool, or deformations resulting from collisions between scene objects detected by a physics engine. We only allocate GPU memory for the faces affected by these modifications to store fine‐scale colour or displacement values. This requires dynamic GPU memory management in order to assign and adaptively apply edits to individual faces at runtime. We present such a memory management technique based on a scan‐operation that is efficiently parallelizable. Since our approach runs entirely on the GPU, we avoid costly CPU–GPU memory transfer and eliminate typical bandwidth limitations. This minimizes runtime overhead to under a millisecond and makes our method ideally suited to many real‐time applications such as video games and interactive authoring tools. In addition, our algorithm significantly reduces storage requirements and allows for much higher resolution content compared to traditional global texturing approaches. Our technique can be applied to various mesh representations, including Catmull–Clark subdivision surfaces, as well as standard triangle and quad meshes. In this paper, we demonstrate several scenarios for these mesh types where our algorithm enables adaptive mesh refinement, local surface deformations and interactive on‐mesh painting and sculpting.

We present a novel method to generate 3D scenes that allow the same activities as real environments captured through noisy and incomplete 3D scans. As robust object detection and instance retrieval from low-quality depth data is challenging, our algorithm aims to model semantically-correct rather than geometrically-accurate object arrangements. Our core contribution is a new scene synthesis technique which, conditioned on a coarse geometric scene representation, models functionally similar scenes using prior knowledge learned from a scene database. The key insight underlying our scene synthesis approach is that many real-world environments are structured to facilitate specific human activities, such as sleeping or eating. We represent scene functionalities through virtual agents that associate object arrangements with the activities for which they are typically used. When modeling a scene, we first identify the activities supported by a scanned environment. We then determine semantically-plausible arrangements of virtual objects -- retrieved from a shape database -- constrained by the observed scene geometry. For a given 3D scan, our algorithm produces a variety of synthesized scenes which support the activities of the captured real environments. In a perceptual evaluation study, we demonstrate that our results are judged to be visually appealing and functionally comparable to manually designed scenes.

We present a method for the real-time transfer of facial expressions from an actor in a source video to an actor in a target video, thus enabling the ad-hoc control of the facial expressions of the target actor. The novelty of our approach lies in the transfer and photorealistic re-rendering of facial deformations and detail into the target video in a way that the newly-synthesized expressions are virtually indistinguishable from a real video. To achieve this, we accurately capture the facial performances of the source and target subjects in real-time using a commodity RGB-D sensor. For each frame, we jointly fit a parametric model for identity, expression, and skin reflectance to the input color and depth data, and also reconstruct the scene lighting. For expression transfer, we compute the difference between the source and target expressions in parameter space, and modify the target parameters to match the source expressions. A major challenge is the convincing re-rendering of the synthesized target face into the corresponding video stream. This requires a careful consideration of the lighting and shading design, which both must correspond to the real-world environment. We demonstrate our method in a live setup, where we modify a video conference feed such that the facial expressions of a different person (e.g., translator) are matched in real-time.

We present a new interactive and online approach to 3D scene understanding. Our system, SemanticPaint , allows users to simultaneously scan their environment whilst interactively segmenting the scene simply by reaching out and touching any desired object or surface. Our system continuously learns from these segmentations, and labels new unseen parts of the environment. Unlike offline systems where capture, labeling, and batch learning often take hours or even days to perform, our approach is fully online. This provides users with continuous live feedback of the recognition during capture, allowing to immediately correct errors in the segmentation and/or learning—a feature that has so far been unavailable to batch and offline methods. This leads to models that are tailored or personalized specifically to the user's environments and object classes of interest, opening up the potential for new applications in augmented reality, interior design, and human/robot navigation. It also provides the ability to capture substantial labeled 3D datasets for training large-scale visual recognition systems.

We present a novel method to obtain fine-scale detail in 3D reconstructions generated with low-budget RGB-D cameras or other commodity scanning devices. As the depth data of these sensors is noisy, truncated signed distance fields are typically used to regularize out the noise, which unfortunately leads to over-smoothed results. In our approach, we leverage RGB data to refine these reconstructions through shading cues, as color input is typically of much higher resolution than the depth data. As a result, we obtain reconstructions with high geometric detail, far beyond the depth resolution of the camera itself. Our core contribution is shading-based refinement directly on the implicit surface representation, which is generated from globally-aligned RGB-D images. We formulate the inverse shading problem on the volumetric distance field, and present a novel objective function which jointly optimizes for fine-scale surface geometry and spatially-varying surface reflectance. In order to enable the efficient reconstruction of sub-millimeter detail, we store and process our surface using a sparse voxel hashing scheme which we augment by introducing a grid hierarchy. A tailored GPU-based Gauss-Newton solver enables us to refine large shape models to previously unseen resolution within only a few seconds.

We present RetroDepth, a new vision-based system for accurately sensing the 3D silhouettes of hands, styluses, and other objects, as they interact on and above physical surfaces. Our setup is simple, cheap, and easily reproducible, comprising of two infrared cameras, diffuse infrared LEDs, and any off-the-shelf retro-reflective material. The retro-reflector aids image segmentation, creating a strong contrast between the surface and any object in proximity. A new highly efficient stereo matching algorithm precisely estimates the 3D contours of interacting objects and the retro-reflective surfaces. A novel pipeline enables 3D finger, hand and object tracking, as well as gesture recognition, purely using these 3D contours. We demonstrate high-precision sensing, allowing robust disambiguation between a finger or stylus touching, pressing or interacting above the surface. This allows many interactive scenarios that seamlessly mix together freehand 3D interactions with touch, pressure and stylus input. As shown, these rich modalities of input are enabled on and above any retro-reflective surface, including custom "physical widgets" fabricated by users. We compare our system with Kinect and Leap Motion, and conclude with limitations and future work.

We present a combined hardware and software solution for markerless reconstruction of non-rigidly deforming physical objects with arbitrary shape in real-time . Our system uses a single self-contained stereo camera unit built from off-the-shelf components and consumer graphics hardware to generate spatio-temporally coherent 3D models at 30 Hz. A new stereo matching algorithm estimates real-time RGB-D data. We start by scanning a smooth template model of the subject as they move rigidly. This geometric surface prior avoids strong scene assumptions, such as a kinematic human skeleton or a parametric shape model. Next, a novel GPU pipeline performs non-rigid registration of live RGB-D data to the smooth template using an extended non-linear as-rigid-as-possible (ARAP) framework. High-frequency details are fused onto the final mesh using a linear deformation model. The system is an order of magnitude faster than state-of-the-art methods, while matching the quality and robustness of many offline algorithms. We show precise real-time reconstructions of diverse scenes, including: large deformations of users' heads, hands, and upper bodies; fine-scale wrinkles and folds of skin and clothing; and non-rigid interactions performed by users on flexible objects such as toys. We demonstrate how acquired models can be used for many interactive scenarios, including re-texturing, online performance capture and preview, and real-time shape and motion re-targeting.

Displacement mapping is ideal for modern GPUs since it enables high-frequency geometric surface detail on models with low memory I/O. However, problems such as texture seams, normal recomputation, and undersampling artifacts have limited its adoption. We provide a comprehensive solution to these problems by introducing a smooth analytic displacement function. Coefficients are stored in a GPU-friendly tile-based texture format, and a multiresolution mip hierarchy of this function is formed. We propose a novel level-of-detail scheme by computing per-vertex adaptive tessellation factors and select the appropriate prefiltered mip levels of the displacement function. Our method obviates the need for a precomputed normal map since normals are directly derived from the displacements. Thus, we are able to perform authoring and rendering simultaneously without typical displacement map extraction from a dense triangle mesh. This not only is more flexible than the traditional combination of discrete displacements and normal maps, but also provides faster runtime due to reduced memory I/O.

Online 3D reconstruction is gaining newfound interest due to the availability of real-time consumer depth cameras. The basic problem takes live overlapping depth maps as input and incrementally fuses these into a single 3D model. This is challenging particularly when real-time performance is desired without trading quality or scale. We contribute an online system for large and fine scale volumetric reconstruction based on a memory and speed efficient data structure. Our system uses a simple spatial hashing scheme that compresses space, and allows for real-time access and updates of implicit surface data, without the need for a regular or hierarchical grid data structure. Surface data is only stored densely where measurements are observed. Additionally, data can be streamed efficiently in or out of the hash table, allowing for further scalability during sensor motion. We show interactive reconstructions of a variety of scenes, reconstructing both fine-grained details and large scale environments. We illustrate how all parts of our pipeline from depth map pre-processing, camera pose estimation, depth map fusion, and surface rendering are performed at real-time rates on commodity graphics hardware. We conclude with a comparison to current state-of-the-art online systems, illustrating improved performance and reconstruction quality.

We present a novel method for high-performance GPU-based rendering of Catmull-Clark subdivision surfaces. Unlike previous methods, our algorithm computes the true limit surface up to machine precision, and is capable of rendering surfaces that conform to the full RenderMan specification for Catmull-Clark surfaces. Specifically, our algorithm can accommodate base meshes consisting of arbitrary valence vertices and faces, and the surface can contain any number and arrangement of semisharp creases and hierarchically defined detail. We also present a variant of the algorithm which guarantees watertight positions and normals, meaning that even displaced surfaces can be rendered in a crack-free manner. Finally, we describe a view-dependent level-of-detail scheme which adapts to both the depth of subdivision and the patch tessellation density. Though considerably more general, the performance of our algorithm is comparable to the best approximating method, and is considerably faster than Stam's exact method.