In this work, we introduce Wonder3D++, a novel method for efficiently generating high-fidelity textured meshes from single-view images. Recent methods based on Score Distillation Sampling (SDS) have shown the potential to recover 3D geometry from 2D diffusion priors, but they typically suffer from time-consuming per-shape optimization and inconsistent geometry. In contrast, certain works directly produce 3D information via fast network inferences, but their results are often of low quality and lack geometric details. To holistically improve the quality, consistency, and efficiency of single-view reconstruction tasks, we propose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images. To ensure the consistency of generation, we employ a multi-view cross-domain attention mechanism that facilitates information exchange across views and modalities. Lastly, we introduce a cascaded 3D mesh extraction algorithm that drives high-quality surfaces from the multi-view 2D representations in only about 3 minute in a coarse-to-fine manner. Our extensive evaluations demonstrate that our method achieves high-quality reconstruction results, robust generalization, and good efficiency compared to prior works.

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

Generating high-quality character animation videos is a fascinating yet challenging task. Existing methods use geometry guidance signals like skeletons, normal maps, or depth maps in a diffusion model to generate character videos from a single reference image. Although these approaches have shown encouraging results, they solely rely on cross attention layers to extract geometry guidance which inevitably leads to temporal inconsistencies and reduced quality. In this paper, we present a novel framework AniFeats to generate high-quality character animation videos. In contrast to existing methods, our key insight is to incorporate explicit features on 3D character meshes during the video generation to achieve significantly improved temporal consistency. Specifically, AniFeats extracts detailed features from the reference image, projects them onto 3D feature meshes based on SMPL-X, and utilizes rendered feature maps from the animated 3D feature meshes as guidance throughout the generation process. This approach directly links local patterns in the input image to those in the output video, effectively strengthening temporal coherence. Extensive experiments demonstrate that AniFeats generates high-quality, temporally consistent character animations with remarkably enhanced realism.

The recent Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model, showcasing potent zero-shot generalization and flexible prompting. Despite SAM finding applications and adaptations in various domains, its primary limitation lies in the inability to grasp object semantics. In this paper, we present Sambor to seamlessly integrate SAM with the open-vocabulary object detector in an end-to-end framework. While retaining all the remarkable capabilities inherent to SAM, we boost it to detect arbitrary objects from human inputs like category names or reference expressions. Building upon the SAM image encoder, we introduce a novel SideFormer module designed to acquire SAM features adept at perceiving objects and inject comprehensive semantic information for recognition. In addition, we devise an Open-set RPN that leverages SAM proposals to assist in finding potential objects. Consequently, Sambor enables the open-vocabulary detector to equally focus on generalizing both localization and classification sub-tasks. Our approach demonstrates superior zero-shot performance across benchmarks, including COCO and LVIS, proving highly competitive against previous state-of-the-art methods. We aspire for this work to serve as a meaningful endeavor in endowing SAM to recognize diverse object categories and advancing open-vocabulary learning with the support of vision foundation models.

Faithfully reconstructing textured shapes and physical properties from videos presents an intriguing yet challenging problem. Significant efforts have been dedicated to advancing such a system identification problem in this area. Previous methods often rely on heavy optimization pipelines with a differentiable simulator and renderer to estimate physical parameters. However, these approaches frequently necessitate extensive hyperparameter tuning for each scene and involve a costly optimization process, which limits both their practicality and generalizability. In this work, we propose a novel framework, Vid2Sim, a generalizable video-based approach for recovering geometry and physical properties through a mesh-free reduced simulation based on Linear Blend Skinning (LBS), offering high computational efficiency and versatile representation capability. Specifically, Vid2Sim first reconstructs the observed configuration of the physical system from video using a feed-forward neural network trained to capture physical world knowledge. A lightweight optimization pipeline then refines the estimated appearance, geometry, and physical properties to closely align with video observations within just a few minutes. Additionally, after the reconstruction, Vid2Sim enables high-quality, mesh-free simulation with high efficiency. Extensive experiments demonstrate that our method achieves superior accuracy and efficiency in reconstructing geometry and physical properties from video data.

The scaling law has been validated in various domains, such as natural language processing (NLP) and massive computer vision tasks; however, its application to motion generation remains largely unexplored. In this paper, we introduce a scalable motion generation framework that includes the motion tokenizer Motion FSQ-VAE and a text-prefix autoregressive transformer. Through comprehensive experiments, we observe the scaling behavior of this system. For the first time, we confirm the existence of scaling laws within the context of motion generation. Specifically, our results demonstrate that the normalized test loss of our prefix autoregressive models adheres to a logarithmic law in relation to compute budgets. Furthermore, we also confirm the power law between Non-Vocabulary Parameters, Vocabulary Parameters, and Data Tokens with respect to compute budgets respectively. Leveraging the scaling law, we predict the optimal transformer size, vocabulary size, and data requirements for a compute budget of 1e18. The test loss of the system, when trained with the optimal model size, vocabulary size, and required data, aligns precisely with the predicted test loss, thereby validating the scaling law. Project page: https://shunlinlu.github.io/ScaMo/

Recent developments in monocular depth estimation methods enable high-quality depth estimation of single-view images but fail to estimate consistent video depth across different frames. Very recent works address this problem by applying a video diffusion model to generate video depth conditioned on the input video, which is training-expensive and can only produce scale-invariant depth values without camera poses. In this paper, we propose a novel video-depth estimation method called Align3R to estimate temporally consistent depth maps for a dynamic video. Our key idea is to utilize the recent DUSt3R model to align estimated monocular depth maps of different timesteps. First, we fine-tune the DUSt3R model with additional estimated monocular depth as inputs for the dynamic scenes. Then, we apply optimization to reconstruct both depth maps and camera poses. Extensive experiments demonstrate that Align3R estimates consistent video depth and camera poses for a monocular video with superior performance than baseline methods.

Synthesizing diverse and physically plausible Human-Scene Interactions (HSI) is pivotal for both computer animation and embodied AI. Despite encouraging progress, current methods mainly focus on developing separate controllers, each specialized for a specific interaction task. This significantly hinders the ability to tackle a wide variety of challenging HSI tasks that require the integration of multiple skills, e.g. sitting down while carrying an object (see Fig. 1). To address this issue, we present TokenHSI, a single, unified transformer-based policy capable of multi-skill unification and flexible adaptation. The key insight is to model the humanoid proprioception as a separate shared token and combine it with distinct task tokens via a masking mechanism. Such a unified policy enables effective knowledge sharing across skills, thereby facilitating the multi-task training. Moreover, our policy architecture supports variable length inputs, enabling flexible adaptation of learned skills to new scenarios. By training additional task tokenizers, we can not only modify the geometries of interaction targets but also coordinate multiple skills to address complex tasks. The experiments demonstrate that our approach can significantly improve versatility, adaptability, and extensibility in various HSI tasks.

Generating diverse and natural human motion sequences based on textual descriptions constitutes a fundamental and challenging research area within the domains of computer vision, graphics, and robotics. Despite significant advancements in this field, current methodologies often face challenges regarding zero-shot generalization capabilities, largely attributable to the limited size of training datasets. Moreover, the lack of a comprehensive evaluation framework impedes the advancement of this task by failing to identify directions for improvement. In this work, we aim to push text-to-motion into a new era, that is, to achieve the generalization ability of zero-shot. To this end, firstly, we develop an efficient annotation pipeline and introduce MotionMillion-the largest human motion dataset to date, featuring over 2,000 hours and 2 million high-quality motion sequences. Additionally, we propose MotionMillion-Eval, the most comprehensive benchmark for evaluating zero-shot motion generation. Leveraging a scalable architecture, we scale our model to 7B parameters and validate its performance on MotionMillion-Eval. Our results demonstrate strong generalization to out-of-domain and complex compositional motions, marking a significant step toward zero-shot human motion generation. The code is available at https://github.com/VankouF/MotionMillion-Codes.

Human motion is highly diverse and dynamic, posing challenges for imitation learning algorithms that aim to generalize motor skills for controlling simulated characters. Previous methods typically rely on a universal full-body controller for tracking reference motion (tracking-based model) or a unified full-body skill embedding space (skill embedding). However, these approaches often struggle to generalize and scale to larger motion datasets. In this work, we introduce a novel skill learning framework, ModSkill, that decouples complex full-body skills into compositional, modular skills for independent body parts. Our framework features a skill modularization attention layer that processes policy observations into modular skill embeddings that guide low-level controllers for each body part. We also propose an Active Skill Learning approach with Generative Adaptive Sampling, using large motion generation models to adaptively enhance policy learning in challenging tracking scenarios. Our results show that this modularized skill learning framework, enhanced by generative sampling, outperforms existing methods in precise full-body motion tracking and enables reusable skill embeddings for diverse goal-driven tasks.

In this paper, we present MVTokenFlow for high-quality 4D content creation from monocular videos. Recent advancements in generative models such as video diffusion models and multiview diffusion models enable us to create videos or 3D models. However, extending these generative models for dynamic 4D content creation is still a challenging task that requires the generated content to be consistent spatially and temporally. To address this challenge, MVTokenFlow utilizes the multiview diffusion model to generate multiview images on different timesteps, which attains spatial consistency across different viewpoints and allows us to reconstruct a reasonable coarse 4D field. Then, MVTokenFlow further regenerates all the multiview images using the rendered 2D flows as guidance. The 2D flows effectively associate pixels from different timesteps and improve the temporal consistency by reusing tokens in the regeneration process. Finally, the regenerated images are spatiotemporally consistent and utilized to refine the coarse 4D field to get a high-quality 4D field. Experiments demonstrate the effectiveness of our design and show significantly improved quality than baseline methods. Project page: https://soolab.github.io/MVTokenFlow.

In this paper, we present a 3D visual grounding method called CityAnchor for localizing an urban object in a city-scale point cloud. Recent developments in multiview reconstruction enable us to reconstruct city-scale point clouds but how to conduct visual grounding on such a large-scale urban point cloud remains an open problem. Previous 3D visual grounding system mainly concentrates on localizing an object in an image or a small-scale point cloud, which is not accurate and efficient enough to scale up to a city-scale point cloud. We address this problem with a multi-modality LLM which consists of two stages, a coarse localization and a fine-grained matching. Given the text descriptions, the coarse localization stage locates possible regions on a projected 2D map of the point cloud while the fine-grained matching stage accurately determines the most matched object in these possible regions. We conduct experiments on the CityRefer dataset and a new synthetic dataset annotated by us, both of which demonstrate our method can produce accurate 3D visual grounding on a city-scale 3D point cloud.

Reconstructing 3D hand-face interactions with deformations from a single image is a challenging yet crucial task with broad applications in AR, VR, and gaming. The challenges stem from self-occlusions during single-view hand-face interactions, diverse spatial relationships between hands and face, complex deformations, and the ambiguity of the single-view setting. The previous state-of-the-art, Decaf, employs a global fitting optimization guided by contact and deformation estimation networks trained on studio-collected data with 3D annotations. However, Decaf suffers from a time-consuming optimization process and limited generalization capability due to its reliance on 3D annotations of hand-face interaction data. To address these issues, we present DICE, the first end-to-end method for Deformation-aware hand-face Interaction reCovEry from a single image. DICE estimates the poses of hands and faces, contacts, and deformations simultaneously using a Transformer-based architecture. It features disentangling the regression of local deformation fields and global mesh vertex locations into two network branches, enhancing deformation and contact estimation for precise and robust hand-face mesh recovery. To improve generalizability, we propose a weakly-supervised training approach that augments the training set using in-the-wild images without 3D ground-truth annotations, employing the depths of 2D keypoints estimated by off-the-shelf models and adversarial priors of poses for supervision. Our experiments demonstrate that DICE achieves state-of-the-art performance on a standard benchmark and in-the- wild data in terms of accuracy and physical plausibility. Additionally, our method operates at an interactive rate (20 fps) on an Nvidia 4090 GPU, whereas Decaf requires more than 15 seconds for a single image. The code will be available at: https://github.com/Qingxuan-Wu/DICE.

Photorealistic 3D full-body human reconstruction from a single image is a critical yet challenging task for applications in films and video games due to inherent ambiguities and severe self-occlusions. While recent approaches leverage SMPL estimation and SMPL-conditioned image generative models to hallucinate novel views, they suffer from inaccurate 3D priors estimated from SMPL meshes and have difficulty in handling difficult human poses and reconstructing fine details.In this paper, we propose SyncHuman, a novel framework that combines 2D multiview generative model and 3D native generative model for the first time, enabling high-quality clothed human mesh reconstruction from single-view images even under challenging human poses.Multiview generative model excels at capturing fine 2D details but struggles with structural consistency, whereas 3D native generative model generates coarse yet structurally consistent 3D shapes. By integrating the complementary strengths of these two approaches, we develop a more effective generation framework. Specifically, we first jointly fine-tune the multiview generative model and the 3D native generative model with proposed pixel-aligned 2D-3D synchronization attention to produce geometrically aligned 3D shapes and 2D multiview images. To further improve details, we introduce a feature injection mechanism that lifts fine details from 2D multiview images onto the aligned 3D shapes, enabling accurate and high-fidelity reconstruction.Extensive experiments demonstrate that SyncHuman achieves robust and photorealistic 3D human reconstruction, even for images with challenging poses. Our method outperforms baseline methods in geometric accuracy and visual fidelity, demonstrating a promising direction for future 3D generation models.

Monocular 3D tracking aims to capture the long-term motion of pixels in 3D space from a single monocular video and has witnessed rapid progress in recent years. However, we argue that the existing monocular 3D tracking methods still fall short in separating the camera motion from foreground dynamic motion and cannot densely track newly emerging dynamic subjects in the videos. To address these two limitations, we propose TrackingWorld, a novel pipeline for dense 3D tracking of almost all pixels within a world-centric 3D coordinate system. First, we introduce a tracking upsampler that efficiently lifts the arbitrary sparse 2D tracks into dense 2D tracks. Then, to generalize the current tracking methods to newly emerging objects, we apply the upsampler to all frames and reduce the redundancy of 2D tracks by eliminating the tracks in overlapped regions. Finally, we present an efficient optimization-based framework to back-project dense 2D tracks into world-centric 3D trajectories by estimating the camera poses and the 3D coordinates of these 2D tracks. Extensive evaluations on both synthetic and real-world datasets demonstrate that our system achieves accurate and dense 3D tracking in a world-centric coordinate frame.

Synthesizing whole-body manipulation of articulated objects, including body motion, hand motion, and object motion, is a critical yet challenging task with broad applications in virtual humans and robotics. The core challenges are twofold. First, achieving realistic whole-body motion requires tight coordination between the hands and the rest of the body, as their movements are interdependent during manipulation. Second, articulated object manipulation typically involves high degrees of freedom and demands higher precision, often requiring the fingers to be placed at specific regions to actuate movable parts. To address these challenges, we propose a novel coordinated diffusion noise optimization framework. Specifically, we perform noise-space optimization over three specialized diffusion models for the body, left hand, and right hand, each trained on its own motion dataset to improve generalization. Coordination naturally emerges through gradient flow along the human kinematic chain, allowing the global body posture to adapt in response to hand motion objectives with high fidelity. To further enhance precision in hand-object interaction, we adopt a unified representation based on basis point sets (BPS), where end-effector positions are encoded as distances to the same BPS used for object geometry. This unified representation captures fine-grained spatial relationships between the hand and articulated object parts, and the resulting trajectories serve as targets to guide the optimization of diffusion noise, producing highly accurate interaction motion. We conduct extensive experiments demonstrating that our method outperforms existing approaches in motion quality and physical plausibility, and enables various capabilities such as object pose control, simultaneous walking and manipulation, and whole-body generation from hand-only data. The code will be released for reproducibility.

Existing video generation models excel at producing photo-realistic videos from text or images, but often lack physical plausibility and 3D controllability. To overcome these limitations, we introduce PhysCtrl, a novel framework for physics-grounded image-to-video generation with physical parameters and force control. At its core is a generative physics network that learns the distribution of physical dynamics across four materials (elastic, sand, plasticine, and rigid) via a diffusion model conditioned on physics parameters and applied forces. We represent physical dynamics as 3D point trajectories and train on a large-scale synthetic dataset of 550K animations generated by physics simulators. We enhance the diffusion model with a novel spatiotemporal attention block that emulates particle interactions and incorporates physics-based constraints during training to enforce physical plausibility. Experiments show that PhysCtrl generates realistic, physics-grounded motion trajectories which, when used to drive image-to-video models, yield high-fidelity, controllable videos that outperform existing methods in both visual quality and physical plausibility. Our code, model and data will be made publicly available upon publication.

Enabling virtual humans to dynamically and realistically respond to diverse auditory stimuli remains a key challenge in character animation, demanding the integration of perceptual modeling and motion synthesis. Despite its significance, this task remains largely unexplored. Most previous works have primarily focused on mapping modalities like speech, audio, and music to generate human motion. As of yet, these models typically overlook the impact of spatial features encoded in spatial audio signals on human motion. To bridge this gap and enable high-quality modeling of human movements in response to spatial audio, we introduce the first comprehensive "Spatial Audio-Driven Human Motion" (SAM) dataset, which contains diverse and high-quality spatial audio and motion data. For benchmarking, we develop a simple yet effective diffusion-based generative framework for human "MOtion generation driven by SPatial Audio," termed MOSPA, which faithfully captures the relationship between body motion and spatial audio through an effective fusion mechanism. Once trained, MOSPA can generate diverse realistic human motions conditioned on varying spatial audio inputs. We perform a thorough investigation of the proposed dataset and conduct extensive experiments for benchmarking, where our method achieves state-of-the-art performance on this task. Our code and model are publicly available at https://github.com/xsy27/Mospa-Acoustic-driven-Motion-Generation.git

The development of intelligent robots seeks to seamlessly integrate them into the human world, providing assistance and companionship in daily life and work, with the ultimate goal of achieving human-robot symbiosis. This requires robots with intelligent interaction abilities to work naturally and effectively with humans. However, current robotic simulators fail to support real human participation, limiting their ability to provide authentic interaction experiences and gather valuable human feedback essential for enhancing robotic capabilities. In this paper, we introduce SymBridge, the first human-in-the-loop cyber-physical interactive system designed to enable the safe and efficient development, evaluation, and optimization of human-robot interaction methods. Specifically, we employ augmented reality technology to enable real humans to interact with virtual robots in physical environments, creating an authentic interactive experience. Building on this, we propose a novel robotic interaction model that generates responsive, precise robot actions in real time through continuous human behavior observation. The model incorporates multi-resolution human motion features and environmental affordances, ensuring contextually adaptive robotic responses. Additionally, SymBridge enables continuous robot learning by collecting human feedback and dynamically adapting the robotic interaction model. By leveraging a designed system architecture and modules, SymBridge builds a bridge between humans and robots, as well as between cyber and physical spaces, providing a natural and realistic interaction experience while facilitating the continuous evolution of robotic intelligence. Extensive experiments, user studies, and robot testing demonstrate the system’s promising performance and highlight its potential to significantly advance research on human-robot symbiosis.

This work studies the challenge of transfer animations between characters whose skeletal topologies differ substantially. While many techniques have advanced retargeting techniques in decades, transfer motions across diverse topologies remains less-explored. The primary obstacle lies in the inherent topological inconsistency between source and target skeletons, which restricts the establishment of straightforward one-to-one bone correspondences. Besides, the current lack of large-scale paired motion datasets spanning different topological structures severely constrains the development of data-driven approaches. To address these limitations, we introduce Motion2Motion, a novel, training-free framework. Simply yet effectively, Motion2Motion works with only one or a few example motions on the target skeleton, by accessing a sparse set of bone correspondences between the source and target skeletons. Through comprehensive qualitative and quantitative evaluations, we demonstrate that Motion2Motion achieves efficient and reliable performance in both similar-skeleton and cross-species skeleton transfer scenarios. The practical utility of our approach is further evidenced by its successful integration in downstream applications and user interfaces, highlighting its potential for industrial applications. Code and data are available at https://lhchen.top/Motion2Motion.

Mixture-of-Experts (MoE) models embody the divide-and-conquer concept and are a promising approach for increasing model capacity, demonstrating excellent scalability across multiple domains. In this paper, we integrate the MoE structure into the classic Vision Transformer (ViT), naming it ViMoE, and explore the potential of applying MoE to vision through a comprehensive study on image classification and semantic segmentation. However, we observe that the performance is sensitive to the configuration of MoE layers, making it challenging to obtain optimal results without careful design. The underlying cause is that inappropriate MoE layers lead to unreliable routing and hinder experts from effectively acquiring helpful information. To address this, we introduce a shared expert to learn and capture common knowledge, serving as an effective way to construct a stable ViMoE. Furthermore, we demonstrate how to analyze expert routing behavior, revealing which MoE layers are capable of specializing in handling specific information and which are not. This provides guidance for retaining the critical layers while removing redundancies, thereby advancing ViMoE to be more efficient without sacrificing accuracy. We aspire for this work to offer new insights into the design of vision MoE models and provide valuable empirical guidance for future research.

Hand-drawn vector sketches often contain implied lines, imprecise intersections, and unintended gaps, making it challenging to identify closed regions for colorization. These challenges become more pronounced as the number of strokes increases. In this paper, we present KISSColor, a novel method for inferring users' intended closed regions. Specifically, we propose intuitive stroke stretching by extending open strokes along tangent isolines of winding-number fields, which provably form geometrically aligned closed regions. Extending all open strokes can lead to overly fragmented regions due to redundant intersections. While a Mixed Integer Programming (MIP) formulation helps reduce redundancy, it is computationally expensive. To improve efficiency, we introduce kinetic stroke stretching, which grows all strokes simultaneously and prioritizes early intersections using a kinetic data structure. This approach preserves stylistic ambiguity for lines requiring long extensions. Based on the growth results, redundant regions are suppressed to minimize fragmentation. We conduct extensive experiments demonstrating the effectiveness of KISSColor, which generates more intuitive partitions, especially for imprecise sketches (see teaser figure). Our code and data will be released upon publication.

Humans possess the ability to master a wide range of motor skills, enabling them to quickly and flexibly adapt to the surrounding environment. Despite recent progress in replicating such versatile human motor skills, existing research often oversimplifies or inadequately captures the complex interplay between human body movements and highly dynamic environments, such as interactions with fluids. In this paper, we present a world model for Character-Fluid Coupling (CFC) for simulating human-fluid interactions via two-way coupling. We introduce a two-level world model which consists of a Physics-Informed Neural Network (PINN)-based model for fluid dynamics and a character world model capturing body dynamics under various external forces. This two-level world model adeptly predicts the dynamics of fluid and its influence on rigid bodies via force prediction, sidestepping the computational burden of fluid simulation and providing policy gradients for efficient policy training. Once trained, our system can control characters to complete high-level tasks while adaptively responding to environmental changes. We also present that the fluid initiates emergent behaviors of the characters, enhancing motion diversity and interactivity. Extensive experiments underscore the effectiveness of CFC, demonstrating its ability to produce high-quality, realistic human-fluid interaction animations.

In this paper, we present WonderHuman to reconstruct dynamic human avatars from a monocular video for high-fidelity novel view synthesis. Previous dynamic human avatar reconstruction methods typically require the input video to have full coverage of the observed human body. However, in daily practice, one typically has access to limited viewpoints, such as monocular front-view videos, making it a cumbersome task for previous methods to reconstruct the unseen parts of the human avatar. To tackle the issue, we present WonderHuman, which leverages 2D generative diffusion model priors to achieve high-quality, photorealistic reconstructions of dynamic human avatars from monocular videos, including accurate rendering of unseen body parts. Our approach introduces a Dual-Space Optimization technique, applying Score Distillation Sampling (SDS) in both canonical and observation spaces to ensure visual consistency and enhance realism in dynamic human reconstruction. Additionally, we present a View Selection strategy and Pose Feature Injection to enforce the consistency between SDS predictions and observed data, ensuring pose-dependent effects and higher fidelity in the reconstructed avatar. In the experiments, our method achieves SOTA performance in producing photorealistic renderings from the given monocular video, particularly for those challenging unseen parts.

In this work, we introduce Wonder3D, a novel method for efficiently generating high-fidelity textured meshes from single-view images. Recent methods based on Score Distillation Sampling (SDS) have shown the potential to recover 3D geometry from 2D diffusion priors, but they typically suffer from time-consuming per-shape optimization and inconsistent geometry. In contrast, certain works di-rectly produce 3D information via fast network inferences, but their results are often of low quality and lack geometric details. To holistically improve the quality, consistency, and efficiency of single-view reconstruction tasks, we pro-pose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images. To ensure the consistency of generation, we employ a multi-view cross-domain attention mechanism that facilitates information exchange across views and modalities. Lastly, we introduce a geometry-aware normal fusion algorithm that extracts high-quality surfaces from the multi-view 2D representations in only 2 r-;» 3 minutes. Our extensive evaluations demonstrate that our method achieves high-quality reconstruction results, robust generalization, and good efficiency compared to prior works.

In this work, we propose a novel method named \textbf{Auto}mated \textbf{P}rocess-\textbf{S}upervised \textbf{V}erifier (\textbf{\textsc{AutoPSV}}) to enhance the reasoning capabilities of large language models (LLMs) by automatically annotating the reasoning steps. \textsc{AutoPSV} begins by training a verification model on the correctness of final answers, enabling it to generate automatic process annotations. This verification model assigns a confidence score to each reasoning step, indicating the probability of arriving at the correct final answer from that point onward. We detect relative changes in the verification's confidence scores across reasoning steps to automatically annotate the reasoning process, enabling error detection even in scenarios where ground truth answers are unavailable. This alleviates the need for numerous manual annotations or the high computational costs associated with model-induced annotation approaches. We experimentally validate that the step-level confidence changes learned by the verification model trained on the final answer correctness can effectively identify errors in the reasoning steps. We demonstrate that the verification model, when trained on process annotations generated by \textsc{AutoPSV}, exhibits improved performance in selecting correct answers from multiple LLM-generated outputs. Notably, we achieve substantial improvements across five datasets in mathematics and commonsense reasoning. The source code of \textsc{AutoPSV} is available at \url{https://github.com/rookie-joe/AutoPSV}.

Abstract We introduce Coverage Axis++, a novel and efficient approach to 3D shape skeletonization. The current state‐of‐the‐art approaches for this task often rely on the watertightness of the input [LWS*15; PWG*19; PWG*19] or suffer from substantial computational costs [DLX*22; CD23], thereby limiting their practicality. To address this challenge, Coverage Axis++ proposes a heuristic algorithm to select skeletal points, offering a high‐accuracy approximation of the Medial Axis Transform (MAT) while significantly mitigating computational intensity for various shape representations. We introduce a simple yet effective strategy that considers shape coverage, uniformity, and centrality to derive skeletal points. The selection procedure enforces consistency with the shape structure while favoring the dominant medial balls, which thus introduces a compact underlying shape representation in terms of MAT. As a result, Coverage Axis++ allows for skeletonization for various shape representations (e.g., water‐tight meshes, triangle soups, point clouds), specification of the number of skeletal points, few hyperparameters, and highly efficient computation with improved reconstruction accuracy. Extensive experiments across a wide range of 3D shapes validate the efficiency and effectiveness of Coverage Axis++. Our codes are available at https://github.com/Frank-ZY-Dou/Coverage_Axis .

Reproducing realistic collective behaviors presents a captivating yet formidable challenge. Traditional rule-based methods rely on hand-crafted principles, limiting motion diversity and realism in generated collective behaviors. Recent imitation learning methods learn from data but often require ground-truth motion trajectories and struggle with authenticity, especially in high-density groups with erratic movements. In this paper, we present a scalable approach, Collective Behavior Imitation Learning (CBIL), for learning fish schooling behavior directly from videos , without relying on captured motion trajectories. Our method first leverages Video Representation Learning, in which a Masked Video AutoEncoder (MVAE) extracts implicit states from video inputs in a self-supervised manner. The MVAE effectively maps 2D observations to implicit states that are compact and expressive for following the imitation learning stage. Then, we propose a novel adversarial imitation learning method to effectively capture complex movements of the schools of fish, enabling efficient imitation of the distribution of motion patterns measured in the latent space. It also incorporates bio-inspired rewards alongside priors to regularize and stabilize training. Once trained, CBIL can be used for various animation tasks with the learned collective motion priors. We further show its effectiveness across different species. Finally, we demonstrate the application of our system in detecting abnormal fish behavior from in-the-wild videos.

In this paper, we introduce a set of simple yet effective TOken REduction (TORE) strategies for Transformer-based Human Mesh Recovery from monocular images. Current SOTA performance is achieved by Transformer-based structures. However, they suffer from high model complexity and computation cost caused by redundant tokens. We propose token reduction strategies based on two important aspects, i.e., the 3D geometry structure and 2D image feature, where we hierarchically recover the mesh geometry with priors from body structure and conduct token clustering to pass fewer but more discriminative image feature tokens to the Transformer. Our method massively reduces the number of tokens involved in high-complexity interactions in the Transformer. This leads to a significantly reduced computational cost while still achieving competitive or even higher accuracy in shape recovery. Extensive experiments across a wide range of benchmarks validate the superior effectiveness of the proposed method. We further demonstrate the generalizability of our method on hand mesh recovery. Visit our project page at https://frank-zy-dou.github.io/projects/Tore/index.html.

We present C · ASE, an efficient and effective framework that learns Conditional Adversarial Skill Embeddings for physics-based characters. C · ASE enables the physically simulated character to learn a diverse repertoire of skills while providing controllability in the form of direct manipulation of the skills to be performed. This is achieved by dividing the heterogeneous skill motions into distinct subsets containing homogeneous samples for training a low-level conditional model to learn the conditional behavior distribution. The skill-conditioned imitation learning naturally offers explicit control over the character’s skills after training. The training course incorporates the focal skill sampling, skeletal residual forces, and element-wise feature masking to balance diverse skills of varying complexities, mitigate dynamics mismatch to master agile motions and capture more general behavior characteristics, respectively. Once trained, the conditional model can produce highly diverse and realistic skills, outperforming state-of-the-art models, and can be repurposed in various downstream tasks. In particular, the explicit skill control handle allows a high-level policy or a user to direct the character with desired skill specifications, which we demonstrate is advantageous for interactive character animation.

Estimating normals with globally consistent orientations for a raw point cloud has many downstream geometry processing applications. Despite tremendous efforts in the past decades, it remains challenging to deal with an unoriented point cloud with various imperfections, particularly in the presence of data sparsity coupled with nearby gaps or thin-walled structures. In this paper, we propose a smooth objective function to characterize the requirements of an acceptable winding-number field, which allows one to find the globally consistent normal orientations starting from a set of completely random normals. By taking the vertices of the Voronoi diagram of the point cloud as examination points, we consider the following three requirements: (1) the winding number is either 0 or 1, (2) the occurrences of 1 and the occurrences of 0 are balanced around the point cloud, and (3) the normals align with the outside Voronoi poles as much as possible. Extensive experimental results show that our method outperforms the existing approaches, especially in handling sparse and noisy point clouds, as well as shapes with complex geometry/topology.

Abstract In this paper, we present a simple yet effective formulation called Coverage Axis for 3D shape skeletonization. Inspired by the set cover problem, our key idea is to cover all the surface points using as few inside medial balls as possible. This formulation inherently induces a compact and expressive approximation of the Medial Axis Transform (MAT) of a given shape. Different from previous methods that rely on local approximation error, our method allows a global consideration of the overall shape structure, leading to an efficient high‐level abstraction and superior robustness to noise. Another appealing aspect of our method is its capability to handle more generalized input such as point clouds and poor‐quality meshes. Extensive comparisons and evaluations demonstrate the remarkable effectiveness of our method for generating compact and expressive skeletal representation to approximate the MAT.

Feature lines are important geometric cues in characterizing the structure of a CAD model. Despite great progress in both explicit reconstruction and implicit reconstruction, it remains a challenging task to reconstruct a polygonal surface equipped with feature lines, especially when the input point cloud is noisy and lacks faithful normal vectors. In this paper, we develop a multistage algorithm, named RFEPS , to address this challenge. The key steps include (1) denoising the point cloud based on the assumption of local planarity, (2) identifying the feature-line zone by optimization of discrete optimal transport, (3) augmenting the point set so that sufficiently many additional points are generated on potential geometry edges, and (4) generating a polygonal surface that interpolates the augmented point set based on restricted power diagram. We demonstrate through extensive experiments that RFEPS, benefiting from the edge-point augmentation and the feature preserving explicit reconstruction, outperforms state of the art methods in terms of the reconstruction quality, especially in terms of the ability to reconstruct missing feature lines.

Motivated by the fact that the medial axis transform is able to encode the shape completely, we propose to use as few medial balls as possible to approximate the original enclosed volume by the boundary surface. We progressively select new medial balls, in a top-down style, to enlarge the region spanned by the existing medial balls. The key spirit of the selection strategy is to encourage large medial balls while imposing given geometric constraints. We further propose a speedup technique based on a provable observation that the intersection of medial balls implies the adjacency of power cells (in the sense of the power crust).We further elaborate the selection rules in combination with two closely related applications. One application is to develop an easy-to-use ball-stick modeling system that helps non-professional users to quickly build a shape with only balls and wires, but any penetration between two medial balls must be suppressed. The other application is to generate porous structures with convex, compact (with a high isoperimetric quotient) and shape-aware pores where two adjacent spherical pores may have penetration as long as the mechanical rigidity can be well preserved.