The lactation performance of Saanen dairy goats, renowned for their high milk yield, is intrinsically linked to their body size, making accurate 3D body measurement essential for assessing milk production potential, yet existing reconstruction methods lack goat-specific authentic 3D data. To address this limitation, we establish the FemaleSaanenGoat dataset containing synchronized eight-view RGBD videos of 55 female Saanen goats (6-18 months). Using multi-view DynamicFusion, we fuse noisy, non-rigid point cloud sequences into high-fidelity 3D scans, overcoming challenges from irregular surfaces and rapid movement. Based on these scans, we develop SaanenGoat, a parametric 3D shape model specifically designed for female Saanen goats. This model features a refined template with 41 skeletal joints and enhanced udder representation, registered with our scan data. A comprehensive shape space constructed from 48 goats enables precise representation of diverse individual variations. With the help of SaanenGoat model, we get high-precision 3D reconstruction from single-view RGBD input, and achieve automated measurement of six critical body dimensions: body length, height, chest width, chest girth, hip width, and hip height. Experimental results demonstrate the superior accuracy of our method in both 3D reconstruction and body measurement, presenting a novel paradigm for large-scale 3D vision applications in precision livestock farming.

Recent advances in generative AI have accelerated the deployment of virtual celebrity agents for commercial endorsements. However, little is known about how their visual style and vocal type, especially when these characteristics are generated via advanced AI reconstruction or voice cloning techniques, affect user trust, perceived realism, familiarity, and social presence. We extracted a representative clip of Sheldon Cooper from The Big Bang Theory as a baseline and generated multiple Sheldon virtual agents that varied in visual style (hand-sculpted, AI-reconstructed, or non-stylized) and vocal type (cloned or synthesized). A 3 × 2 within-subjects experiment (N = 30) revealed that visual style significantly affected user trust, perceived realism, familiarity, and social presence, while vocal type affected only perceived realism and familiarity. Comparisons between the virtual agents and the video baseline confirmed that even cutting-edge 3D modeling still differs significantly from authentic video representations. Behavioral data indicate that the relationship between interpersonal-distance variations and trust levels is not a simple linear one. These findings provide actionable guidance for designers leveraging generative AI to create trustworthy virtual avatars or agents and delineate new research avenues for virtual celebrity agents.

Photorealistic 3D human modeling is essential for various applications and has seen tremendous progress. However, existing methods for monocular full-body reconstruction, typically relying on front and/or predicted back view, still struggle with satisfactory performance due to the ill-posed nature of the problem and sophisticated self-occlusions. In this paper, we propose PSHuman, a novel framework that explicitly reconstructs human meshes utilizing priors from the multiview diffusion model. It is found that directly applying multiview diffusion on single-view human images leads to severe geometric distortions, especially on generated faces. To address it, we propose a cross-scale diffusion that models the joint probability distribution of global full-body shape and local facial characteristics, enabling identity-preserved novel-view generation without geometric distortion. Moreover, to enhance cross-view body shape consistency of varied human poses, we condition the generative model on parametric models (SMPL-X), which provide body priors and prevent unnatural views inconsistent with human anatomy. Leveraging the generated multiview normal and color images, we present SMPLX-initialized explicit human carving to recover realistic textured human meshes efficiently. Extensive experiments on CAPE and THuman2.1 demonstrate PSHuman’s superiority in geometry details, texture fidelity, and generalization capability.

Light field microscopy (LFM) has gained significant attention due to its ability to capture snapshot-based, large-scale 3D fluorescence images. However, existing LFM reconstruction algorithms are highly sensitive to sensor noise or require hard-to-get ground-truth annotated data for training. To address these challenges, this paper introduces V2V3D, an unsupervised view2view-based framework that establishes a new paradigm for joint optimization of image denoising and 3D reconstruction in a unified architecture. We assume that the LF images are derived from a consistent 3D signal, with the noise in each view being independent. This enables V2V3D to incorporate the principle of noise2noise for effective denoising. To enhance the recovery of high-frequency details, we propose a novel wave-optics-based feature alignment technique, which transforms the point spread function, used for forward propagation in wave optics, into convolution kernels specifically designed for feature alignment. Moreover, we introduce an LFM dataset containing LF images and their corresponding 3D intensity volumes. Extensive experiments demonstrate that our approach achieves high computational efficiency and outperforms the other state-of-the-art methods. These advancements position V2V3D as a promising solution for 3D imaging under challenging conditions. Our code and dataset will be publicly accessible at https://joey1998hub.github.io/V2V3D/.

Incompressible fluid on the surface is an interesting research area in the fluid simulation, which is the fundamental building block in visual effects, design of liquid crystal films, scientific analyses of atmospheric and oceanic phenomena, etc. The task brings two key challenges: the extension of the physical laws on 3D surfaces and the preservation of the energy and volume. Traditional methods rely on grids or meshes for spatial discretization, which leads to high memory consumption and a lack of robustness and adaptivity for various mesh qualities and representations. Many implicit representations based simulators like INSR are proposed for the storage efficiency and continuity, but they face challenges in the surface simulation and the energy dissipation. We propose a neural physical simulation framework on the surface with the implicit neural representation. Our method constructs a parameterized vector field with the exterior calculus and Closest Point Method on the surfaces, which guarantees the divergence-free property and enables the simulation on different surface representations (e.g. implicit neural represented surfaces). We further adopt a corresponding covariant derivative based advection process for surface flow dynamics and energy preservation. Our method shows higher accuracy, flexibility and memory-efficiency in the simulations of various surfaces with low energy dissipation. Numerical studies also highlight the potential of our framework across different practical applications such as vorticity shape generation and vector field Helmholtz decomposition.

Novel space-time view synthesis for monocular video is a highly challenging task: both static and dynamic objects usually appear in the video, but only a single view of the current scene is available, resulting in inaccurate synthesis results. To address this challenge, we propose FRNeRF, a novel space-time view synthesis method with a fusion regularization field. Specifically, we design a 2D-3D fusion regularization field for the original dynamic neural field, which helps reduce blurring of dynamic objects in the scene. In addition, we add image prior features to the hierarchical sampling to solve the problem that the traditional hierarchical sampling strategy cannot obtain sufficient sampling points during training. We evaluate our method extensively on multiple datasets and show the results of dynamic space-time view synthesis. Our method achieves state-of-the-art performance both qualitatively and quantitatively. Code is available for research purposes at https://cic.tju.edu.cn/faculty/likun/projects/FRNerf.

Existing human pose estimation methods seldom consider the impact or constraint of different types of contact. In this paper, we elaborate on the impact of both body-scene contact and self-contact on pose estimation and refer to them as general contact. First, we extend existing datasets by calculating additional contact labels for general contact inference. Moreover, based on the extended dataset, we present the first network to predict dense general contact from a single RGB image. Finally, we develop a novel optimization method that successfully utilizes the inferred general contact information for accurate 3D pose estimation. Our results show that knowledge of contact can provide strong constraints and resolve pose ambiguity, thus significantly improving human pose estimation accuracy, especially for challenging poses that cannot be well handled by existing methods. Experimental results and comparisons further demonstrate the effectiveness of the proposed method. Our results are even more reasonable than certain pseudo-ground truth determined from multi-view images.

Neural implicit representation, the parameterization of a continuous distance function as a Multi-Layer Perceptron (MLP), has emerged as a promising lead in tackling surface reconstruction from unoriented point clouds. In the presence of noise, however, its lack of explicit neighborhood connectivity makes sharp edges identification particularly challenging, hence preventing the separation of smoothing and sharpening operations, as is achievable with its discrete counterparts. In this work, we propose to tackle this challenge with an auxiliary field, the octahedral field. We observe that both smoothness and sharp features in the distance field can be equivalently described by the smoothness in octahedral space. Therefore, by aligning and smoothing an octahedral field alongside the implicit geometry, our method behaves analogously to bilateral filtering, resulting in a smooth reconstruction while preserving sharp edges. Despite being operated purely pointwise, our method outperforms various traditional and neural implicit fitting approaches across extensive experiments, and is very competitive with methods that require normals and data priors. Code and data of our work are available at: https://github.com/Ankbzpx/frame-field.

With the continuous advancement of artificial intelligence technology, data-driven methods for reconstructing and animating virtual agents have achieved increasing levels of realism. However, there is limited research on how these novel data-driven methods, combined with voice cues, affect user perceptions. We use advanced data-driven methods to reconstruct stylized agents and combine them with synthesized voices to study their effects on users' trust and other perceptions (e.g. social presence and empathy). Through an experiment with 27 participants, our findings reveal that stylized virtual agents enhance user trust to a degree comparable to real style, while voice has a negligible effect on trust. Additionally, elder agents are more likely to be trusted. The style of the agents also plays a key role in participants' perceived realism, and audio-visual matching significantly enhances perceived empathy. These results provide new insights into designing trustworthy virtual agents and further support and validate the audio-visual integration theory.

The neural radiance field (NeRF) achieved remarkable success in modeling 3D scenes and synthesizing high-fidelity novel views. However, existing NeRF-based methods focus more on making full use of high-resolution images to generate high-resolution novel views, but less considering the generation of high-resolution details given only low-resolution images. In analogy to the extensive usage of image super-resolution, NeRF super-resolution is an effective way to generate low-resolution-guided high-resolution 3D scenes and holds great potential applications. Up to now, such an important topic is still under-explored. In this article, we propose a NeRF super-resolution method, named Super-NeRF, to generate high-resolution NeRF from only low-resolution inputs. Given multi-view low-resolution images, Super-NeRF constructs a multi-view consistency-controlling super-resolution module to generate various view-consistent high-resolution details for NeRF. Specifically, an optimizable latent code is introduced for each input view to control the generated reasonable high-resolution 2D images satisfying view consistency. The latent codes of each low-resolution image are optimized synergistically with the target Super-NeRF representation to utilize the view consistency constraint inherent in NeRF construction. We verify the effectiveness of Super-NeRF on synthetic, real-world, and even AI-generated NeRFs. Super-NeRF achieves state-of-the-art NeRF super-resolution performance on high-resolution detail generation and cross-view consistency.

This article proposes a hybrid radiance field representation for unbounded immersive light field reconstruction which supports high-quality rendering and aggressive view extrapolation. The key idea is to first formally separate the foreground and the background and then adaptively balance learning of them during the training process. To fulfill this goal, we represent the foreground and background as two separate radiance fields with two different spatial mapping strategies. We further propose an adaptive sampling strategy and a segmentation regularizer for more clear segmentation and robust convergence. Finally, we contribute a novel immersive light field dataset, named THUImmersive, with the potential to achieve much larger space 6DoF immersive rendering effects compared with existing datasets, by capturing multiple neighboring viewpoints for the same scene, to stimulate the research and AR/VR applications in the immersive light field domain. Extensive experiments demonstrate the strong performance of our method for unbounded immersive light field reconstruction.

We present a general, fast, and practical solution for interpolating novel views of diverse real-world scenes given a sparse set of nearby views. Existing generic novel view synthesis methods rely on time-consuming scene geometry pre-computation or redundant sampling of the entire space for neural volumetric rendering, limiting the overall efficiency. Instead, we incorporate learned MVS priors into the neural volume rendering pipeline while improving the rendering efficiency by reducing sampling points under the guidance of depth probability distributions. Specifically, fewer but important points are sampled under the guidance of depth probability distributions extracted from the learned MVS architecture. Based on the learned probability-guided sampling, we develop a sophisticated neural volume rendering module that effectively integrates source view information with the learned scene structures. We further propose confidence-aware refinement to improve the rendering results in uncertain, occluded, and unreferenced regions. Moreover, we build a four-view camera system for holographic display and provide a real-time version of our framework for free-viewpoint experience, where novel view images of a spatial resolution of 512×512 can be rendered at around 20 fps on a single GTX 3090 GPU. Experiments show that our method achieves 15 to 40 times faster rendering compared to state-of-the-art baselines, with strong generalization capacity and comparable high-quality novel view synthesis performance.

We explore the generalization of the implicit representation in the physical simulation task. Traditional time-dependent partial differential equations (PDEs) solvers for physical simulation often adopt the grid or mesh for spatial discretization, which is memory-consuming for high resolution and lack of adaptivity. Many implicit representations like local extreme machine or Siren are proposed but they are still too compact to suffer from limited accuracy in handling local details and a long time of convergence. We contribute a neural simulation framework based on multi-resolution hash grid representation to introduce hierarchical consideration of global and local information, simultaneously. Furthermore, we propose two key strategies: 1) a numerical gradient method for computing high-order derivatives with boundary conditions; 2) a range analysis sample method for fast neural geometry boundary sampling with dynamic topologies. Our method shows much higher accuracy and strong flexibility for various simulation problems: e.g., large elastic deformations, complex fluid dynamics, and multi-scale phenomena which remain challenging for existing neural physical solvers.

Recent years have witnessed a trend of the deep integration of the generation and reconstruction paradigms. In this paper, we extend the ability of controllable generative models for a more comprehensive hand mesh recovery task: di-rect hand mesh generation, inpainting, reconstruction, and fitting in a single framework, which we name as Holistic Hand Mesh Recovery (HHMR). Our key observation is that different kinds of hand mesh recovery tasks can be achieved by a single generative model with strong multimodal con-trollability, and in such a framework, realizing different tasks only requires giving different signals as conditions. To achieve this goal, we propose an all-in-one diffusion frame-work based on graph convolution and attention mechanisms for holistic hand mesh recovery. In order to achieve strong control generation capability while ensuring the decoupling of multimodal control signals, we map different modalities to a shared feature space and apply cross-scale random masking in both modality and feature levels. In this way, the correlation between different modalities can be fully exploited during the learning of hand priors. Furthermore, we propose Condition-aligned Gradient Guidance to enhance the alignment of the generated model with the control sig-nals, which significantly improves the accuracy of the hand mesh reconstruction and fitting. Experiments show that our novel framework can realize multiple hand mesh recovery tasks simultaneously and outperform the existing methods in different tasks, which provides more possibilities for sub-sequent downstream applications including gesture recognition, pose generation, mesh editing, and so on.

Existing diffusion models for pose-guided human video generation mostly suffer from temporal inconsistency in the generated appearance and poses due to the inherent randomization nature of the generation process. In this paper, we propose a novel framework, DiffPerformer, to synthesize high-fidelity and temporally consistent human video. Without complex architecture modification or costly training, DiffPerformer finetunes a pre-trained diffusion model on a single video of the target character and introduces an implicit video representation as a proxy to learn temporally consistent guidance for the diffusion model. The guidance is encoded into VAE latent space and an iterative optimization loop is constructed between the implicit video representation and the diffusion model, allowing to harness the smooth property of the implicit video representation and the generative capabilities of the diffusion model in a mutually beneficial way. Moreover, we propose 3D-aware human flow as a temporal constraint during the optimization to explicitly model the correspondence between driving poses and human appearance. This alleviates the mis-alignment between driving poses and target performer and therefore maintains the appearance coherence under various motions. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods. The code is available at https://github.com/aipixel/DiffPerformer.

Towards holistic understanding of 3D scenes, a general 3D segmentation method is needed that can segment diverse objects without restrictions on object quantity or categories, while also reflecting the inherent hierarchical structure. To achieve this, we propose OmniSeg3D, an omniversal segmentation method aims for segmenting anything in 3D all at once. The key insight is to lift multi-view inconsistent 2D segmentations into a consistent 3D feature field through a hierarchical contrastive learning framework, which is accomplished by two steps. Firstly, we design a novel hierarchical representation based on category-agnostic 2D segmentations to model the multi-level relationship among pixels. Secondly, image features rendered from the 3D feature field are clustered at different levels, which can be further drawn closer or pushed apart according to the hierarchical relationship between different levels. In tackling the challenges posed by inconsistent 2D segmentations, this framework yields a global consistent 3D feature field, which further enables hierarchical segmentation, multi-object selection, and global discretization. Extensive experiments demonstrate the effectiveness of our method on high-quality 3D segmentation and accurate hierarchical structure understanding. A graphical user interface further facilitates flexible interaction for omniversal 3D segmentation.

Foot contact is an important cue for human motion capture, understanding, and generation. Existing datasets tend to annotate dense foot contact using visual matching with thresholding or incorporating pressure signals. However, these approaches either suffer from low accuracy or are only designed for small-range and slow motion. There is still a lack of a vision-pressure multimodal dataset with large-range and fast human motion, as well as accurate and dense foot-contact annotation. To fill this gap, we propose a Multimodal MoCap Dataset with Vision and Pressure sensors, named MMVP. MMVP provides accurate and dense plantar pressure signals synchronized with RGBD observations, which is especially useful for both plausible shape estimation, robust pose fitting without foot drifting, and accurate global translation tracking. To validate the dataset, we propose an RGBD-P SMPL fitting method and also a monocular-video-based baseline framework, VP-MoCap, for human motion capture. Experiments demonstrate that our RGBD-P SMPL Fitting results significantly outperform pure visual motion capture. Moreover, VP-MoCap outperforms SOTA methods in foot-contact and global translation estimation accuracy. We believe the configuration of the dataset and the baseline frameworks will stimulate the research in this direction and also provide a good reference for MoCap applications in various domains. Project page: https://metaverse-ai-lab-thu.github.io/MMVP-Dataset/

Light field disparity estimation is an essential task in computer vision. Currently, supervised learning-based methods have achieved better performance than both unsupervised and optimization-based methods. However, the generalization capacity of supervised methods on real-world data, where no ground truth is available for training, remains limited. In this paper, we argue that unsupervised methods can achieve not only much stronger generalization capacity on real-world data but also more accurate disparity estimation results on synthetic datasets. To fulfill this goal, we present the Occlusion Pattern Aware Loss, named OPAL, which successfully extracts and encodes general occlusion patterns inherent in the light field for calculating the disparity loss. OPAL enables: i) accurate and robust disparity estimation by teaching the network how to handle occlusions effectively and ii) significantly reduced network parameters required for accurate and efficient estimation. We further propose an EPI transformer and a gradient-based refinement module for achieving more accurate and pixel-aligned disparity estimation results. Extensive experiments demonstrate our method not only significantly improves the accuracy compared with SOTA unsupervised methods, but also possesses stronger generalization capacity on real-world data compared with SOTA supervised methods. Last but not least, the network training and inference efficiency are much higher than existing learning-based methods. Our code will be made publicly available.

In this paper, we touch on the problem of markerless multi-modal human motion capture especially for string performance capture which involves inherently subtle hand-string contacts and intricate movements. To fulfill this goal, we first collect a dataset, named String Performance Dataset (SPD), featuring cello and violin performances. The dataset includes videos captured from up to 23 different views, audio signals, and detailed 3D motion annotations of the body, hands, instrument, and bow. Moreover, to acquire the detailed motion annotations, we propose an audio-guided multi-modal motion capture framework that explicitly incorporates hand-string contacts detected from the audio signals for solving detailed hand poses. This framework serves as a baseline for string performance capture in a completely markerless manner without imposing any external devices on performers, eliminating the potential of introducing distortion in such delicate movements. We argue that the movements of performers, particularly the sound-producing gestures, contain subtle information often elusive to visual methods but can be inferred and retrieved from audio cues. Consequently, we refine the vision-based motion capture results through our innovative audio-guided approach, simultaneously clarifying the contact relationship between the performer and the instrument, as deduced from the audio. We validate the proposed framework and conduct ablation studies to demonstrate its efficacy. Our results outperform current state-of-the-art vision-based algorithms, underscoring the feasibility of augmenting visual motion capture with audio modality. To the best of our knowledge, SPD is the first dataset for musical instrument performance, covering fine-grained hand motion details in a multi-modal, large-scale collection. It holds significant implications and guidance for string instrument pedagogy, animation, and virtual concerts, as well as for both musical performance analysis and generation. Our code and SPD dataset are available at https://github.com/Yitongishere/string_performance.

Recent neural rendering methods have made great progress in generating photorealistic human avatars. However, these methods are generally conditioned only on low-dimensional driving signals (e.g., body poses), which are insufficient to encode the complete appearance of a clothed human. Hence they fail to generate faithful details. To address this problem, we exploit driving view images (e.g., in telepresence systems) as additional inputs. We propose a novel neural rendering pipeline, Hybrid Volumetric-Textural Rendering (HVTR++), which synthesizes 3D human avatars from arbitrary driving poses and views while staying faithful to appearance details efficiently and at high quality. First, we learn to encode the driving signals of pose and view image on a dense UV manifold of the human body surface and extract UV-aligned features, preserving the structure of a skeleton-based parametric model. To handle complicated motions (e.g., self-occlusions), we then leverage the UV-aligned features to construct a 3D volumetric representation based on a dynamic neural radiance field. While this allows us to represent 3D geometry with changing topology, volumetric rendering is computationally heavy. Hence we employ only a rough volumetric representation using a pose- and image-conditioned downsampled neural radiance field (PID-NeRF), which we can render efficiently at low resolutions. In addition, we learn 2D textural features that are fused with rendered volumetric features in image space. The key advantage of our approach is that we can then convert the fused features into a high-resolution, high-quality avatar by a fast GAN-based textural renderer. We demonstrate that hybrid rendering enables HVTR++ to handle complicated motions, render high-quality avatars under user-controlled poses/shapes, and most importantly, be efficient at inference time. Our experimental results also demonstrate state-of-the-art quantitative results.

In this paper, we aim to address the challenge of novel view rendering of human performers that wear clothes with complex texture patterns using a sparse set of camera views. Although some recent works have achieved remarkable rendering quality on humans with relatively uniform textures using sparse views, the rendering quality remains limited when dealing with complex texture patterns as they are unable to recover the high-frequency geometry details that are observed in the input views. To this end, we propose HDhuman, which uses a human reconstruction network with a pixel-aligned spatial transformer and a rendering network with geometry-guided pixel-wise feature integration to achieve high-quality human reconstruction and rendering. The designed pixel-aligned spatial transformer calculates the correlations between the input views and generates human reconstruction results with high-frequency details. Based on the surface reconstruction results, the geometry-guided pixel-wise visibility reasoning provides guidance for multi-view feature integration, enabling the rendering network to render high-quality images at 2k resolution on novel views. Unlike previous neural rendering works that always need to train or fine-tune an independent network for a different scene, our method is a general framework that is able to generalize to novel subjects. Experiments show that our approach outperforms all the prior generic or specific methods on both synthetic data and real-world data. Source code and test data will be made publicly available for research purposes at http://cic.tju.edu.cn/faculty/likun/projects/HDhuman/index.html.

Detailed 3D reconstruction and photo-realistic relighting of digital humans are essential for various applications. To this end, we propose a novel sparse-view 3d human reconstruction framework that closely incorporates the occupancy field and albedo field with an additional visibility field-it not only resolves occlusion ambiguity in multi-view feature aggregation, but can also be used to evaluate light attenuation for self-shadowed relighting. To enhance its training viability and efficiency, we discretize visibility onto a fixed set of sample directions and supply it with coupled geometric 3D depth feature and local 2D image feature. We further propose a novel rendering-inspired loss, namely TransferLoss, to implicitly enforce the alignment between visibility and occupancy field, enabling end-to-end joint training. Results and extensive experiments demonstrate the effectiveness of the proposed method, as it surpasses state-of-the-art in terms of reconstruction accuracy while achieving comparably accurate relighting to ray-traced ground truth.

This paper proposes a method for fast scene radiance field reconstruction with strong novel view synthesis performance and convenient scene editing functionality. The key idea is to fully utilize semantic parsing and primitive extraction for constraining and accelerating the radiance field reconstruction process. To fulfill this goal, a primitive-aware hybrid rendering strategy was proposed to enjoy the best of both volumetric and primitive rendering. We further contribute a reconstruction pipeline conducts primitive parsing and radiance field learning iteratively for each input frame which successfully fuses semantic, primitive, and radiance information into a single framework. Extensive evaluations demonstrate the fast reconstruction ability, high rendering quality, and convenient editing functionality of our method.

This paper presents Triangulation Residual loss (TR loss) for multiview 3D pose estimation in a data-efficient manner. Existing 3D supervised models usually require large-scale 3D annotated datasets, but the amount of existing data is still insufficient to train supervised models to achieve ideal performance, especially for animal pose estimation. To employ unlabeled multiview data for training, previous epipolar-based consistency provides a self-supervised loss that considers only the local consistency in pairwise views, resulting in limited performance and heavy calculations. In contrast, TR loss enables self-supervision with global multiview geometric consistency. Starting from initial 2D keypoint estimates, the TR loss can fine-tune the corresponding 2D detector without 3D supervision by simply minimizing the smallest singular value of the triangulation matrix in an end-to-end fashion. Our method achieves the state-of-the-art 25.8mm MPJPE and competitive 28.7mm MPJPE with only 5\% 2D labeled training data on the Human3.6M dataset. Experiments on animals such as mice demonstrate our TR loss's data-efficient training ability.

Garment representation, editing and animation are challenging topics in the area of computer vision and graphics. It remains difficult for existing garment representations to achieve smooth and plausible transitions between different shapes and topologies. In this work, we introduce, DeepCloth, a unified framework for garment representation, reconstruction, animation and editing. Our unified framework contains 3 components: First, we represent the garment geometry with a "topology-aware UV-position map", which allows for the unified description of various garments with different shapes and topologies by introducing an additional topology-aware UV-mask for the UV-position map. Second, to further enable garment reconstruction and editing, we contribute a method to embed the UV-based representations into a continuous feature space, which enables garment shape reconstruction and editing by optimization and control in the latent space, respectively. Finally, we propose a garment animation method by unifying our neural garment representation with body shape and pose, which achieves plausible garment animation results leveraging the dynamic information encoded by our shape and style representation, even under drastic garment editing operations. To conclude, with DeepCloth, we move a step forward in establishing a more flexible and general 3D garment digitization framework. Experiments demonstrate that our method can achieve state-of-the-art garment representation performance compared with previous methods.

In this paper, we propose a controllable high-quality free viewpoint video generation method based on the motion graph and neural radiance fields (NeRF). Different from existing pose-driven NeRF or time/structure conditioned NeRF works, we propose to first construct a directed motion graph of the captured sequence. Such a sequence-motion-parameterization strategy not only enables flexible pose control for free viewpoint video rendering but also avoids redundant calculation of similar poses and thus improves the overall reconstruction efficiency. Moreover, to support body shape control without losing the realistic free viewpoint rendering performance, we improve the vanilla NeRF by combining explicit surface deformation and implicit neural scene representations. Specifically, we train a local surface-guided NeRF for each valid frame on the motion graph, and the volumetric rendering was only performed in the local space around the real surface, thus enabling plausible shape control ability. As far as we know, our method is the first method that supports both realistic free viewpoint video reconstruction and motion graph-based user-guided motion traversal. The results and comparisons further demonstrate the effectiveness of the proposed method.

We propose a novel neural rendering pipeline, Hybrid Volumetric-Textural Rendering (HVTR), which synthesizes virtual human avatars from arbitrary poses efficiently and at high quality. First, we learn to encode articulated human motions on a dense UV manifold of the human body surface. To handle complicated motions (e.g., self-occlusions), we then leverage the encoded information on the UV manifold to construct a 3D volumetric representation based on a dynamic pose-conditioned neural radiance field. While this allows us to represent 3D geometry with changing topology, volumetric rendering is computationally heavy. Hence we employ only a rough volumetric representation using a pose-conditioned downsampled neural radiance field (PD-NeRF), which we can render efficiently at low resolutions. In addition, we learn 2D textural features that are fused with rendered volumetric features in image space. The key advantage of our approach is that we can then convert the fused features into a high-resolution, high-quality avatar by a fast GAN-based textural renderer. We demonstrate that hybrid rendering enables HVTR to handle complicated motions, render high-quality avatars under user-controlled poses/shapes and even loose clothing, and most importantly, be efficient at inference time. Our experimental results also demonstrate state-of-the-art quantitative results. More results are available at our project page: https://www.cs.umd.edu/~taohu/hvtr/

Graph convolutional network (GCN) has achieved great success in single hand reconstruction task, while interacting two-hand reconstruction by GCN remains unexplored. In this paper, we present Interacting Attention Graph Hand (IntagHand), the first graph convolution based network that reconstructs two interacting hands from a single RGB image. To solve occlusion and interaction challenges of two-hand reconstruction, we introduce two novel attention based modules in each upsampling step of the original GCN. The first module is the pyramid image feature attention (PIFA) module, which utilizes multiresolution features to implicitly obtain vertex-to-image alignment. The second module is the cross hand attention (CHA) module that encodes the coherence of interacting hands by building dense cross-attention between two hand vertices. As a result, our model outperforms all existing two-hand re-construction methods by a large margin on InterHand2.6M benchmark. Moreover, ablation studies verify the effectiveness of both PIFA and CHA modules for improving the reconstruction accuracy. Results on in-the-wild images and live video streams further demonstrate the generalization ability of our network. Our code is available at https://github.com/Dw1010/IntagHand.

We introduce DoubleField, a novel framework combining the merits of both surface field and radiance field for high-fidelity human reconstruction and rendering. Within DoubleField, the surface field and radiance field are associated together by a shared feature embedding and a surface-guided sampling strategy. Moreover, a view-to-view transformer is introduced to fuse multi-view features and learn view-dependent features directly from high-resolution inputs. With the modeling power of DoubleField and the view-to-view transformer, our method significantly improves the reconstruction quality of both geometry and appearance, while supporting direct inference, scene-specific high-resolution finetuning, and fast rendering. The efficacy of DoubleField is validated by the quantitative evaluations on several datasets and the qualitative results in a real-world sparse multi-view system, showing its superior capability for high-quality human model reconstruction and photo-realistic free-viewpoint human rendering. Data and source code will be made public for the research purpose.

We present FaceVerse, a fine-grained 3D Neural Face Model, which is built from hybrid East Asian face datasets containing 60K fused RGB-D images and 2K high-fidelity 3D head scan models. A novel coarse-to-fine structure is proposed to take better advantage of our hybrid dataset. In the coarse module, we generate a base parametric model from large-scale RGB-D images, which is able to predict accurate rough 3D face models in different genders, ages, etc. Then in the fine module, a conditional StyleGAN architecture trained with high-fidelity scan models is introduced to enrich elaborate facial geometric and texture details. Note that different from previous methods, our base and detailed modules are both changeable, which enables an innovative application of adjusting both the basic attributes and the facial details of 3D face models. Furthermore, we propose a single-image fitting framework based on differentiable rendering. Rich experiments show that our method outperforms the state-of-the-art methods.

It is extremely challenging to create an animatable clothed human avatar from RGB videos, especially for loose clothes due to the difficulties in motion modeling. To address this problem, we introduce a novel representation on the basis of recent neural scene rendering techniques. The core of our representation is a set of structured local radiance fields, which are anchored to the pre-defined nodes sampled on a statistical human body template. These local radiance fields not only leverage the flexibility of implicit representation in shape and appearance modeling, but also factorize cloth deformations into skeleton motions, node residual translations and the dynamic detail variations inside each individual radiance field. To learn our representation from RGB data and facilitate pose generalization, we propose to learn the node translations and the detail variations in a conditional generative latent space. Overall, our method enables automatic construction of animatable human avatars for various types of clothes without the need for scanning subject-specific templates, and can generate realistic images with dynamic details for novel poses. Experiment show that our method outperforms state-of-the-art methods both qualitatively and quantitatively.

In this paper, we propose an efficient method for robust and accurate 3D self-portraits using a single RGBD camera. Our method can generate detailed and realistic 3D self-portraits in seconds and shows the ability to handle subjects wearing extremely loose clothes. To achieve highly efficient and robust reconstruction, we propose PIFusion, which combines learning-based 3D recovery with volumetric non-rigid fusion to generate accurate sparse partial scans of the subject. Meanwhile, a non-rigid volumetric deformation method is proposed to continuously refine the learned shape prior. Moreover, a lightweight bundle adjustment algorithm is proposed to guarantee that all the partial scans can not only "loop" with each other but also remain consistent with the selected live key observations. Finally, to further generate realistic portraits, we propose non-rigid texture optimization to improve the texture quality. Additionally, we also contribute a benchmark for single-view 3D self-portrait reconstruction, an evaluation dataset that contains 10 single-view RGBD sequences of a self-rotating performer wearing various clothes and the corresponding ground-truth 3D models in the first frame of each sequence. The results and experiments based on this dataset show that the proposed method outperforms state-of-the-art methods on accuracy, efficiency, and generality.

Modeling 3D humans accurately and robustly from a single image is very challenging, and the key for such an ill-posed problem is the 3D representation of the human models. To overcome the limitations of regular 3D representations, we propose Parametric Model-Conditioned Implicit Representation (PaMIR), which combines the parametric body model with the free-form deep implicit function. In our PaMIR-based reconstruction framework, a novel deep neural network is proposed to regularize the free-form deep implicit function using the semantic features of the parametric model, which improves the generalization ability under the scenarios of challenging poses and various clothing topologies. Moreover, a novel depth-ambiguity-aware training loss is further integrated to resolve depth ambiguities and enable successful surface detail reconstruction with imperfect body reference. Finally, we propose a body reference optimization method to improve the parametric model estimation accuracy and to enhance the consistency between the parametric model and the implicit function. With the PaMIR representation, our framework can be easily extended to multi-image input scenarios without the need of multi-camera calibration and pose synchronization. Experimental results demonstrate that our method achieves state-of-the-art performance for image-based 3D human reconstruction in the cases of challenging poses and clothing types.

We introduce MulayCap, a novel human performance capture method using a monocular video camera without the need for pre-scanning. The method uses "multi-layer" representations for geometry reconstruction and texture rendering, respectively. For geometry reconstruction, we decompose the clothed human into multiple geometry layers, namely a body mesh layer and a garment piece layer. The key technique behind is a Garment-from-Video (GfV) method for optimizing the garment shape and reconstructing the dynamic cloth to fit the input video sequence, based on a cloth simulation model which is effectively solved with gradient descent. For texture rendering, we decompose each input image frame into a shading layer and an albedo layer, and propose a method for fusing a fixed albedo map and solving for detailed garment geometry using the shading layer. Compared with existing single view human performance capture systems, our "multi-layer" approach bypasses the tedious and time consuming scanning step for obtaining a human specific mesh template. Experimental results demonstrate that MulayCap produces realistic rendering of dynamically changing details that has not been achieved in any previous monocular video camera systems. Benefiting from its fully semantic modeling, MulayCap can be applied to various important editing applications, such as cloth editing, re-targeting, relighting, and AR applications.

Human volumetric capture is a long-standing topic in computer vision and computer graphics. Although high-quality results can be achieved using sophisticated off-line systems, real-time human volumetric capture of complex scenarios, especially using light-weight setups, remains challenging. In this paper, we propose a human volumetric capture method that combines temporal volumetric fusion and deep implicit functions. To achieve high-quality and temporal-continuous reconstruction, we propose dynamic sliding fusion to fuse neighboring depth observations together with topology consistency. Moreover, for detailed and complete surface generation, we propose detailpreserving deep implicit functions for RGBD input which can not only preserve the geometric details on the depth inputs but also generate more plausible texturing results. Results and experiments show that our method outperforms existing methods in terms of view sparsity, generalization capacity, reconstruction quality, and run-time efficiency.

We propose POseguided SElective Fusion (POSEFu-sion), a single-view human volumetric capture method that leverages tracking-based methods and tracking-free inference to achieve high-fidelity and dynamic 3D reconstruction. By contributing a novel reconstruction framework which contains pose-guided keyframe selection and robust implicit surface fusion, our method fully utilizes the advantages of both tracking-based methods and tracking-free inference methods, and finally enables the high-fidelity recon-struction of dynamic surface details even in the invisible regions. We formulate the keyframe selection as a dynamic programming problem to guarantee the temporal continuity of the reconstructed sequence. Moreover, the novel robust implicit surface fusion involves an adaptive blending weight to preserve high-fidelity surface details and an automatic collision handling method to deal with the potential self-collisions. Overall, our method enables high-fidelity and dynamic capture in both visible and invisible regions from a single RGBD camera, and the results and experiments show that our method outperforms state-of-the-art methods.

Deep implicit functions (DIFs), as a kind of 3D shape representation, are becoming more and more popular in the 3D vision community due to their compactness and strong representation power. However, unlike polygon mesh-based templates, it remains a challenge to reason dense correspondences or other semantic relationships across shapes represented by DIFs, which limits its applications in texture transfer, shape analysis and so on. To overcome this limitation and also make DIFs more interpretable, we propose Deep Implicit Templates, a new 3D shape representation that supports explicit correspondence reasoning in deep implicit representations. Our key idea is to formulate DIFs as conditional deformations of a template implicit function. To this end, we propose Spatial Warping LSTM, which de-composes the conditional spatial transformation into multiple point-wise transformations and guarantees generalization capability. Moreover, the training loss is carefully designed in order to achieve high reconstruction accuracy while learning a plausible template with accurate correspondences in an unsupervised manner. Experiments show that our method can not only learn a common implicit tem-plate for a collection of shapes, but also establish dense correspondences across all the shapes simultaneously with-out any supervision.

Multi-person total motion capture is extremely challenging when it comes to handle severe occlusions, different reconstruction granularities from body to face and hands, drastically changing observation scales and fast body movements. To overcome these challenges above, we contribute a lightweight total motion capture system for multi-person interactive scenarios using only sparse multi-view cameras. By contributing a novel hand and face bootstrapping algorithm, our method is capable of efficient localization and accurate association of the hands and faces even on severe occluded occasions. We leverage both pose regression and keypoints detection methods and further propose a unified two-stage parametric fitting method for achieving pixel-aligned accuracy. Moreover, for extremely self-occluded poses and close interactions, a novel feedback mechanism is proposed to propagate the pixel-aligned reconstructions into the next frame for more accurate association. Overall, we propose the first light-weight total capture system and achieves fast, robust and accurate multi-person total motion capture performance. The results and experiments show that our method achieves more accurate results than existing methods under sparse-view setups.

We propose DeepMultiCap, a novel method for multi-person performance capture using sparse multi-view cameras. Our method can capture time varying surface details without the need of using pre-scanned template models. To tackle with the serious occlusion challenge for close interacting scenes, we combine a recently proposed pixel-aligned implicit function with parametric model for robust reconstruction of the invisible surface areas. An effective attention-aware module is designed to obtain the fine-grained geometry details from multi-view images, where high-fidelity results can be generated. In addition to the spatial attention method, for video inputs, we further propose a novel temporal fusion method to alleviate the noise and temporal inconsistencies for moving character reconstruction. For quantitative evaluation, we contribute a high quality multi-person dataset, MultiHuman, which consists of 150 static scenes with different levels of occlusions and ground truth 3D human models. Experimental results demonstrate the state-of-the-art performance of our method and the well generalization to real multiview video data, which outperforms the prior works by a large margin.

In this paper, we propose an efficient method for robust 3D self-portraits using a single RGBD camera. Benefiting from the proposed PIFusion and lightweight bundle adjustment algorithm, our method can generate detailed 3D self-portraits in seconds and shows the ability to handle subjects wearing extremely loose clothes. To achieve highly efficient and robust reconstruction, we propose PIFusion, which combines learning-based 3D recovery with volumetric non-rigid fusion to generate accurate sparse partial scans of the subject. Moreover, a non-rigid volumetric deformation method is proposed to continuously refine the learned shape prior. Finally, a lightweight bundle adjustment algorithm is proposed to guarantee that all the partial scans can not only ``loop'' with each other but also remain consistent with the selected live key observations. The results and experiments show that the proposed method achieves more robust and efficient 3D self-portraits compared with state-of-the-art methods.

his paper contributes a novel realtime multi-person motion capture algorithm using multiview video inputs. Due to the heavy occlusions and closely interacting motions in each view, joint optimization on the multiview images and multiple temporal frames is indispensable, which brings up the essential challenge of realtime efficiency. To this end, for the first time, we unify per-view parsing, cross-view matching, and temporal tracking into a single optimization framework, i.e., a 4D association graph that each dimension (image space, viewpoint and time) can be treated equally and simultaneously. To solve the 4D association graph efficiently, we further contribute the idea of 4D limb bundle parsing based on heuristic searching, followed with limb bundle assembling by proposing a bundle Kruskal's algorithm. Our method enables a realtime motion capture system running at 30fps using 5 cameras on a 5-person scene. Benefiting from the unified parsing, matching and tracking constraints, our method is robust to noisy detection due to severe occlusions and close interacting motions, and achieves high-quality online pose reconstruction quality. The proposed method outperforms state-of-the-art methods quantitatively without using high-level appearance information.

A high-quality 4D geometry and texture reconstruction for human activities usually requires multiview perceptions via highly structured multi-camera setup, where both the specifically designed cameras and the tedious pre-calibration restrict the popularity of professional multi-camera systems for daily applications. In this paper, we propose UnstructuredFusion, a practicable realtime markerless human performance capture method using unstructured commercial RGBD cameras. Along with the flexible hardware setup using simply three unstructured RGBD cameras without any careful pre-calibration, the challenge 4D reconstruction through multiple asynchronous videos is solved by proposing three novel technique contributions, i.e., online multi-camera calibration, skeleton warping based non-rigid tracking, and temporal blending based atlas texturing. The overall insights behind lie in the solid global constraints of human body and human motion which are modeled by the skeleton and the skeleton warping, respectively. Extensive experiments such as allocating three cameras flexibly in a handheld way demonstrate that the proposed UnstructuredFusion achieves high-quality 4D geometry and texture reconstruction without tiresome pre-calibration, liberating the cumbersome hardware and software restrictions in conventional structured multi-camera system, while eliminating the inherent occlusion issues of the single camera setup.

We propose DoubleFusion, a new real-time system that combines volumetric non-rigid reconstruction with data-driven template fitting to simultaneously reconstruct detailed surface geometry, large non-rigid motion and the optimized human body shape from a single depth camera. One of the key contributions of this method is a double-layer representation consisting of a complete parametric body model inside, and a gradually fused detailed surface outside. A pre-defined node graph on the body parameterizes the non-rigid deformations near the body, and a free-form dynamically changing graph parameterizes the outer surface layer far from the body, which allows more general reconstruction. We further propose a joint motion tracking method based on the double-layer representation to enable robust and fast motion tracking performance. Moreover, the inner parametric body is optimized online and forced to fit inside the outer surface layer as well as the live depth input. Overall, our method enables increasingly denoised, detailed and complete surface reconstructions, fast motion tracking performance and plausible inner body shape reconstruction in real-time. Experiments and comparisons show improved fast motion tracking and loop closure performance on more challenging scenarios. Two extended applications including body measurement and shape retargeting show the potential of our system in terms of practical use.

We present a neural hand reconstruction method for monocular 3D hand pose and shape estimation in this paper. Instead of directly representing hand with 3D data, a novel UV position map is introduced to represent hand pose and shape with 2D data, which maps 3D hand surface points to 2D image space. Furthermore, an encoder-decoder neural network is proposed to infer such UV position map from only single image. To train such network with the lack of ground truth training pairs, we propose a novel MANOReg module which employs MANO model as shape prior to constrain high-dimensional space of UV position map. Both quantitative and qualitative experiments demonstrate the effectiveness of our UV position map representation and MANOReg module.

This paper proposes a new method for live free-viewpoint human performance capture with dynamic details (e.g., cloth wrinkles) using a single RGBD camera. Our main contributions are: (i) a multi-layer representation of garments and body, and (ii) a physics-based performance capture procedure. We first digitize the performer using multi-layer surface representation, which includes the undressed body surface and separate clothing meshes. For performance capture, we perform skeleton tracking, cloth simulation, and iterative depth fitting sequentially for the incoming frame. By incorporating cloth simulation into the performance capture pipeline, we can simulate plausible cloth dynamics and cloth-body interactions even in the occluded regions, which was not possible in previous capture methods. Moreover, by formulating depth fitting as a physical process, our system produces cloth tracking results consistent with the depth observation while still maintaining physical constraints. Results and evaluations show the effectiveness of our method. Our method also enables new types of applications such as cloth retargeting, free-viewpoint video rendering and animations.

We propose DeepHuman, an image-guided volume-to-volume translation CNN for 3D human reconstruction from a single RGB image. To reduce the ambiguities associated with the reconstruction of invisible areas, our method leverages a dense semantic representation generated from SMPL model as an additional input. One key feature of our network is that it fuses different scales of image features into the 3D space through volumetric feature transformation, which helps to recover accurate surface geometry. The surface details are further refined through a normal refinement network, which can be concatenated with the volume generation network using our proposed volumetric normal projection layer. We also contribute THuman, a 3D real-world human model dataset containing approximately 7000 models. The network is trained using training data generated from the dataset. Overall, due to the specific design of our network and the diversity in our dataset, our method enables 3D human model estimation given only a single image and outperforms state-of-the-art approaches.

We propose DoubleFusion, a new real-time system that combines volumetric dynamic reconstruction with data-driven template fitting to simultaneously reconstruct detailed geometry, non-rigid motion and the inner human body shape from a single depth camera. One of the key contributions of this method is a double layer representation consisting of a complete parametric body shape inside, and a gradually fused outer surface layer. A pre-defined node graph on the body surface parameterizes the non-rigid deformations near the body, and a free-form dynamically changing graph parameterizes the outer surface layer far from the body, which allows more general reconstruction. We further propose a joint motion tracking method based on the double layer representation to enable robust and fast motion tracking performance. Moreover, the inner body shape is optimized online and forced to fit inside the outer surface layer. Overall, our method enables increasingly denoised, detailed and complete surface reconstructions, fast motion tracking performance and plausible inner body shape reconstruction in real-time. In particular, experiments show improved fast motion tracking and loop closure performance on more challenging scenarios.

We propose BodyFusion, a novel real-time geometry fusion method that can track and reconstruct non-rigid surface motion of a human performance using a single consumer-grade depth camera. To reduce the ambiguities of the non-rigid deformation parameterization on the surface graph nodes, we take advantage of the internal articulated motion prior for human performance and contribute a skeleton-embedded surface fusion (SSF) method. The key feature of our method is that it jointly solves for both the skeleton and graph-node deformations based on information of the attachments between the skeleton and the graph nodes. The attachments are also updated frame by frame based on the fused surface geometry and the computed deformations. Overall, our method enables increasingly denoised, detailed, and complete surface reconstruction as well as the updating of the skeleton and attachments as the temporal depth frames are fused. Experimental results show that our method exhibits substantially improved nonrigid motion fusion performance and tracking robustness compared with previous state-of-the-art fusion methods. We also contribute a dataset for the quantitative evaluation of fusion-based dynamic scene reconstruction algorithms using a single depth camera.

This article proposes a real-time method that uses a single-view RGB-D input (a depth sensor integrated with a color camera) to simultaneously reconstruct a casual scene with a detailed geometry model, surface albedo, per-frame non-rigid motion, and per-frame low-frequency lighting, without requiring any template or motion priors. The key observation is that accurate scene motion can be used to integrate temporal information to recover the precise appearance, whereas the intrinsic appearance can help to establish true correspondence in the temporal domain to recover motion. Based on this observation, we first propose a shading-based scheme to leverage appearance information for motion estimation. Then, using the reconstructed motion, a volumetric albedo fusing scheme is proposed to complete and refine the intrinsic appearance of the scene by incorporating information from multiple frames. Since the two schemes are iteratively applied during recording, the reconstructed appearance and motion become increasingly more accurate. In addition to the reconstruction results, our experiments also show that additional applications can be achieved, such as relighting, albedo editing, and free-viewpoint rendering of a dynamic scene, since geometry, appearance, and motion are all reconstructed by our technique.