We present a data-driven approach for physics-based, muscle-driven dexterous control that enables musculoskeletal hands to perform precise piano playing for novel pieces of music outside the reference dataset. Our approach combines high-frequency muscle-level control with low-frequency latent-space coordination in a hierarchical architecture. At the low level, general single-hand policies are trained via reinforcement learning to generate dynamic muscle-tendon activations while tracking trajectories from a large reference motion dataset. The resulting tracking policies are then distilled into variational autoencoder (VAE) models, yielding smooth and structured latent spaces that abstract away low-level muscle dynamics. For the high level, we train piece-specific policies to operate in this latent space, coordinating bimanual motions based on specific goals, denoted by note events extracted from given musical scores, to synthesize performances beyond the reference data. High-level control is formulated as a decentralized multiagent reinforcement learning problem combined with adversarial learning for motion imitation. In addition, we present an enhanced musculoskeletal hand model that supports fine control of fingers for accurate low-level motion tracking and diverse high-level motion synthesis. We evaluate the control pipeline of our approach on a diverse piano repertoire spanning multiple musical styles and technical demands. Results demonstrate that our approach can synthesize coordinated bimanual motions with accurate key presses, and achieve the state-of-the-art performance of piano playing in physics-based dexterous control, while generalizing to sheet music that is not presented in the reference dataset. We also show that our musculoskeletal hand model demonstrates superior biomechanical stability and tracking precision compared to the existing model, and validate that our musculoskeletal hand model and muscle-driven controller can generate physiologically plausible activation patterns that align with human electromyography (EMG) recordings when subjects perform multiple tasks.
论文检索
输入标题、作者或关键词，从 10,462 篇学术成果中精准定位
Monte Carlo integration is widely used in computer graphics, especially in rendering, but we identify two key limitations. First, for each sample, we can often obtain rich auxiliary information, such as sample position, or geometric information. However, a classical Monte Carlo estimator cannot effectively use this information and only averages the function values. Second, the Monte Carlo formulation makes it difficult to adapt the sampling distribution toward truly informative regions, which can be critical for reconstructing the signal. To address these limitations, we argue that a sampler and integrator beyond the standard Monte Carlo methods is needed. We therefore propose an end-to-end sampling-integration approach that jointly learns both a sampler and an integrator using neural networks, enabling samples to be drawn and used in a more coupled and principled manner. By training on a dataset of integrands, the estimator can further use learned priors over integrand structure and specialize to a family of problems. We evaluate our method on diverse applications in lighting, transmittance, generalized winding number, and walk-on-spheres, spanning both linear and nonlinear cases, and a broad range of low- and high-dimensional settings. Even though the networks add computational overheads, in the equal-sample setting, our method achieves substantial improvements, providing a powerful alternative to traditional quadrature rules and sampling methods.
Supporting a wide variety of motion styles is critical for creating diverse virtual characters, but current methods either require large stylized datasets or pre-trained models that cannot generalize beyond their training distribution. We present STyMo, a few-shot approach that learns motion style from only seconds of paired data and trains in one to two minutes. Our key insight is to decompose style into two components: a static component capturing time-invariant posture, and a temporal component capturing frame-wise dynamics. This decomposition yields an interpretable system where posture intensity, temporal exaggeration, and per-body-region style can be adjusted at runtime. Furthermore, the reduction in required training data and computation time structurally permits an iterative authoring workflow. To ensure robustness on arbitrary inputs, we further introduce a stylizability gate that automatically prevents artifacts on out-of-distribution motions. We demonstrate results across diverse motion styles, from subtle emotional variations to exaggerated character archetypes, and release our processed paired dataset to facilitate future research. The source code used in this paper can be found at: https://github.com/facebookresearch/STyMo
Animatable 3D assets, defined as geometry equipped with an articulated skeleton and skinning weights, are fundamental to interactive graphics, embodied agents, and animation production. While recent 3D generative models can synthesize visually plausible shapes from images, the results are typically static. Obtaining usable rigs via post-hoc auto-rigging is brittle and often produces skeletons that are topologically inconsistent with the generated geometry. We present AniGen, a unified framework that directly generates animate-ready 3D assets conditioned on a single image. Our key insight is to represent shape, skeleton, and skinning as mutually consistent S3 Fields (Shape, Skeleton, Skin) defined over a shared spatial domain. To enable the robust learning of these fields, we introduce two technical innovations: (i) a confidence-decaying skeleton field that explicitly handles the geometric ambiguity of bone prediction at Voronoi boundaries, and (ii) a dual skin feature field that decouples skinning weights from specific joint counts, allowing a fixed-architecture network to predict rigs of arbitrary complexity. Built upon a two-stage flow-matching pipeline, AniGen first synthesizes a sparse structural scaffold and then generates dense geometry and articulation in a structured latent space. Extensive experiments demonstrate that AniGen substantially outperforms state-of-the-art sequential baselines in rig validity and animation quality, generalizing effectively to in-the-wild images across diverse categories including animals, humanoids, and machinery. Homepage: https://yihua7.github.io/AniGen_web/
Despite recent advancements in native latent diffusion models for single-view 3D generation, they still suffer from inadequate geometric details due to the global entanglement of VecSet-based representations and inaccurate structural topology arising from single-view ambiguity. Existing solutions often rely on model scaling over large-scale datasets to improve fidelity, which is computationally prohibitive and inefficient in capturing fine-grained details. In this work, we propose Tempo3D, a resource-efficient paradigm for high-fidelity VecSet-based 3D generation via efficient temporal-aware fine-tuning and multi-view latent aggregation. Our approach consists of two critical components: (1) To facilitate robust detail learning, we establish the TempoDetail dataset and design the Time-Segmented LoRA (TS-LoRA) module. TS-LoRA exploits the inherent "structure-to-details" temporal transition of flow-based models to decouple feature learning, significantly bolstering the capacity to produce high-frequency details without large-scale retraining. (2) To mitigate geometric inaccuracies stemming from single-view ambiguity, we propose a multi-view latent aggregation strategy incorporating Soft Flow Trajectory Projection (Soft FTP) and Score-based Velocity Field Aggregation (SVFA). By aggregating reference views derived from Multimodal Large Language Models (MLLMs), these components resolve the intrinsic conflicts between velocity vectors caused by cross-view latent discrepancies, thereby preventing geometric collapse and ensuring directional consistency. Moreover, the integration of MLLMs empowers Tempo3D to support precise semantic 3D editing via natural language prompts while maintaining structural integrity. Experiments demonstrate that Tempo3D outperforms state-of-the-art baselines in generation quality, geometric precision, and editability under a highly efficient computational budget.
Following the success of deep neural networks in 2D pose estimation, reconstruction-based approaches have significantly advanced multi-person 3D pose estimation from sparse multi-view images. These methods typically detect 2D poses independently in each view and then associate them for 3D reconstruction. However, despite strong progress, recent state-of-the-art methods still face critical limitations: 1) They often depend on global optimization over a large and complex set of multi-view 2D joints to jointly infer 3D poses for all individuals, making the process highly complex and prone to suboptimal solutions; 2) Their tight coupling with the bottom-up detector OpenPose hinders the use of more advanced top-down or single-stage 2D pose estimators and restricts the integration of richer instance-level cues learned by these models. To address these limitations, we propose TwinPose, a novel framework that alleviates the complexity of global pose inference by optimizing within person-specific 3D pose subspaces, while fully supporting diverse 2D pose detectors and effectively leveraging pose-instance cues. The key idea is to introduce a twin pose — a 3D counterpart of each 2D pose — that inherits its instance representation and aggregates geometrically consistent 2D joints from other views. All twin poses are unified in a common 3D space, where those belonging to the same individual naturally share a number of bones. This structural property enables association by counting shared bones, forming person-specific subspaces from which each individual's 3D pose can be inferred independently in an efficient and robust manner. Extensive experiments demonstrate that TwinPose achieves state-of-the-art performance in both accuracy and efficiency across multiple public and proprietary datasets. Importantly, it is fully detector-agnostic, allowing seamless integration with current and future advances in 2D pose estimation while remaining highly robust to noisy or imperfect 2D predictions. Project page with code and additional resources: https://github.com/zgspose/TwinPose
Recent work in 3D deep learning has demonstrated that unsigned distance functions (UDFs) are a useful representation for 3D reconstruction and shape generation because they can represent surfaces with arbitrary topology. However, extracting meshes that preserve the intended topology, especially in the presence of non-manifold structures, remains challenging. We present DCx, an extension of the standard Dual Contouring (DC) method which was originally proposed for isosurface extraction from signed distance functions (SDFs). Standard DC operates on individual voxels and inserts one vertex per active cube, where activation is determined by detecting sign changes. To address the lack of sign information in UDFs, DCx adopts an optimization-based strategy for determining active cubes. It operates on each 2 × 2 × 2 voxel block, referred to as an expanded cube, and introduces a voxel-to-mesh lookup table that stores connectivity patterns based on local voxel configurations. This enables efficient triangle extraction using predefined templates. These changes improve upon DC by avoiding failure cases caused by unreliable active-cube detection in UDFs and by correcting mesh connections in non-manifold regions. As a result, DCx supports the extraction of both manifold and non-manifold surfaces from neural UDFs. DCx is conceptually simple and easy to implement. Experimental results show that DCx produces meshes with higher accuracy in a more robust way than existing methods, particularly on shapes with complex geometry or non-manifold structures. The source code is available at http://github.com/jjjkkyz/DCx.
The explosion of generative 3D assets has created a massive demand for animation, yet current motion capture methods remain brittle, restricted to species-specific templates (e.g., SMPL) or requiring labor-intensive manual rigging. We introduce TopoCap, the first unified framework capable of extracting motion from monocular video and retargeting it onto characters with arbitrary, unseen skeletal topologies, i.e., from bipeds to hexapods and inanimate objects, without test-time optimization. Our key insight is that while skeletal structures are combinatorial and discrete, the underlying physics of motion occupy a continuous, low-dimensional manifold. We materialize this insight via a two-stage generative pipeline. First, we learn a Universal Motion Manifold using a Graph CVAE that compresses heterogeneous kinematic chains into a shared, fixed-length latent code. By explicitly conditioning the decoder on a structural embedding of the target rig, we disentangle motion dynamics from skeletal topology. Second, we treat video-to-animation as a conditional flow matching problem, predicting these topology-agnostic codes from visual features. To learn this generalized prior, we introduce Mobjaverse, a massive-scale dataset curated from Objaverse-XL. Comprising over 5,000 unique skeletal topologies and 2 million frames, it exceeds the structural diversity of existing datasets by two orders of magnitude. Extensive experiments demonstrate that TopoCapoutperforms specialist models on human and quadruped benchmarks while enabling zero-shot retargeting for the long tail of 3D creatures. Dataset is publicly available at https://huggingface.co/datasets/duckduckplz/Mobjaverse
Photography is the art of painting with light, yet nighttime scenes are shaped by competing degradations: intense flares obscure scene structure, while photon-limited regions collapse into noise. Conventional approaches address these factors in isolation, overlooking the fact that these degradations are fundamentally entangled. To bridge this gap, we introduce LUCID, a unified framework that reframes nighttime restoration as a continuous and controllable process rather than a fixed correction. We decompose nighttime restoration into two cooperative components: a flare disentanglement module that lifts the ’curtain’ of optical artifacts to provide reliable structural guidance, and a diffusion-driven module that leverages generative priors to reconstruct clean and well-exposed imagery. Crucially, LUCID introduces explicit controllability through a novel four-mode training strategy, enabling users to steer the restoration process via classifier-free guidance (CFG) and allowing selective control over light sources and their associated flare and ghosting artifacts, while also supporting high dynamic range (HDR) reconstruction through continuous exposure control. Extensive experiments demonstrate that LUCID consistently outperforms state-of-the-art methods across diverse real-world nighttime scenarios.
Artistic styles often embed abstraction beyond surface appearance, involving deliberate reinterpretation of structure rather than mere changes in texture or color. Conventional style transfer methods typically preserve the input geometry and therefore struggle to capture this deeper abstraction behavior, especially for illustrative and non-photorealistic styles. In this work, we introduce Abstraction in Style (AiS), a generative framework that separates structural abstraction from visual stylization. Given a target image and a small set of style exemplars, AiS first derives an intermediate abstraction proxy that reinterprets the target’s structure in accordance with the abstraction logic exhibited by the style. The proxy captures semantic structure while relaxing geometric fidelity, enabling subsequent stylization to operate on an abstracted representation rather than the original image. In a second stage, the abstraction proxy is rendered to produce the final stylized output, preserving visual coherence with the reference style. Both stages are implemented using a shared image-space analogy, enabling transformations to be learned from visual exemplars without explicit geometric supervision. By decoupling abstraction from appearance and treating abstraction as an explicit, transferable process, AiS supports a wider range of stylistic transformations, improves controllability, and enables more expressive stylization.
Geometry optimization often encounters sparse gradients from limited observations, which can cause optimization to drift toward unnatural shapes. Prior work stabilizes this process by exploiting spatial structure encoded by the Laplacian operator within a single shape, enforcing spatial smoothness on gradients. However, such smoothness alone propagates gradients to unobserved regions without any prior knowledge of how shapes typically deform in a given domain. We introduce statistical gradient filtering, which leverages statistical structure across a shape collection by learning shape variations via principal component analysis (PCA) and guiding geometry updates along directions consistent with this learned prior. Unlike previous PCA-based methods that constrain solutions to a linear subspace or modify the objective with regularization terms, we filter gradients at each iteration to steer the optimization path toward plausible shapes, without restricting the solution space or altering the original objective. We validate our approach across a range of shape optimization tasks, demonstrating robust convergence even under challenging conditions.
Motion warping is a core technique in character animation that enables the adaptation of existing motion data to novel spatio-temporal constraints. Conventional motion warping methods often rely on heuristic modifications that can violate physical consistency or introduce visual artifacts. More recent learning-based editing approaches improve realism, but many of them encode motion into tightly entangled latent space, which makes them struggle to balance editing flexibility and content preservation. To address this, we propose a novel deep motion warping framework that explicitly disentangles the motion structure from global and stylistic attributes for intuitive motion editing. Our key insight is to leverage learned phase features as a continuous and robust representation of the underlying structure, and explicitly disentangle motion into root velocity, phase, and learned latent variables using a phase-conditioned diffusion autoencoder. This design supports a wide range of editing operations, including root motion warping, motion exaggeration, time warping, and style transfer by directly manipulating decoupled components, without requiring paired training data. Extensive experiments demonstrate that our approach enables high-level, flexible motion editing while strictly preserving the structural consistency and physical plausibility of the source motion
Developing controllers capable of completing a wide range of tasks in a natural and life-like manner is a key challenge in enabling practical applications of physics-based character animation. In this work, we introduce Generative Pretrained Controllers (GPC), which leverage tokenization and next-token modeling to create general-purpose, reusable generative controllers from large-scale motion datasets. Our framework utilizes end-to-end reinforcement learning to jointly optimize a "motion vocabulary", modeled via Finite Scalar Quantization (FSQ), along with a corresponding control policy that can map the discrete codes to physics-based controls. After the "codebook" has been learned, the underlying structure of this large vocabulary is modeled by training a GPT-style autoregressive transformer, leading to a powerful generative controller that generates controls for a physically simulated character by performing next-token prediction. Once the generative controller has been trained, we propose a suite of adaptation techniques for finetuning the controller for new downstream tasks. Our proposed framework greatly simplifies the training process compared to previous tokenized methods, and achieves a 99.98% success rate in reproducing a vast corpus of motion clips. The generative controller exhibits a variety of natural emergent behaviors, such as responsive behaviors to perturbations and recovery behaviors after falling. This results in highly robust general purpose controllers for a variety of downstream applications.
Meshes are among the most common 3D scene representations, but directly generating meshes is challenging largely because the mesh representation contains many structures, such as permutation invariance of vertices or faces. To address this challenge, we present a novel approach that learns to generate triangle meshes represented as triangle soups. We adopt equivariant optimal-transport flow matching models that respect key symmetries within the triangle soup representation, including permutation invariance among faces and among vertices within each of the faces. Toward this goal, we propose a simple yet effective modification to the state-of-the-art Diffusion Transformer architecture, resulting in a scalable network capable of modeling a flow field while maintaining the desirable symmetries (equivariance). Moreover, we introduce a loss function grounded in optimal transport principles that improves model convergence by eliminating training signals that violate these symmetries. Our model can achieve performance comparable to state-of-the-art auto-regressive mesh generators while providing about an 18× speedup during inference.
Boundary Representation (B-rep) is the most commonly used data format in Computer-Aided Design (CAD) due to its analytical precision and direct support for parametric editing. However, its heterogeneous data structure— continuous parametric geometry with discrete topological graphs—poses fundamental challenges for deep learning models. Existing methods often directly predict the heterogeneous B-rep graph, relying on fixed-size padding or sequential tokenization to handle the varying cardinality of the geometric primitives. These approaches struggle with the combinatorial complexity of CAD models. The discrete, non-differentiable nature of the graph data structure prevents end-to-end optimization of the geometry and watertightness. In this work we introduce DualBrep, a novel continuous representation that unifies B-rep geometry and topology within a fully structured Euclidean domain. DualBrep encodes a CAD model using dual scalar fields: a Signed Distance Function (SDF) to represent the global shape geometry, and an Unsigned Distance Field (UDF) that implicitly encodes the topological structure via a Voronoi partitioning of the surface elements. Rather than processing these fields independently, we compress them into a single latent space. While the dual-field formulation alone already gives reconstruction a flexible, primitive-free segmentation signal that adapts to arbitrary face counts and surface types, the shared latent also makes generation tractable: a Flow Matching model can sample geometry and topology jointly from a single code, avoiding the error accumulation that plagues sequential or autoregressive B-rep predictors. Finally, we use a neural rebuilder to extract explicit B-rep models—comprising both prismatic and free-form primitives—directly from our continuous dual scalar fields. We demonstrate that DualBrep serves as a robust, unified backbone for CAD B-rep learning, achieving strong performance in both reverse engineering from raw point clouds and generative modeling via latent flow matching. Code is available at https://github.com/AutodeskAILab/DualBrep.
Despite recent progress, text-to-image models still struggle to generate semantically diverse and compositionally accurate multi-person interaction scenes, often collapsing to repetitive layouts, stereotypical poses, and poorly grounded interactions. In this work, we bridge this gap by introducing a dual pose–image representation that brings person-centric structural priors into pretrained diffusion transformers. Our model jointly predicts a 2D pose visualization image and its corresponding RGB image, enabling structure and appearance to co-evolve during learning. At its core, a cross-modal alignment scheme binds text, pose, and image representations, ensuring consistent grounding across modalities. Furthermore, we design an iterative scene construction scheme, progressively generating complex multi-human interactions while effectively decomposing the overall generation complexity. Extensive experiments demonstrate that our method substantially improves prompt alignment and scene diversity in multi-person image generation.
A lesson plan (LP) is a structured guide outlining instructional objectives, methods, and assessments to ensure organized learning. However, existing LP creations are often time-consuming, inconsistent in structure, and lack pedagogical mechanisms for real-time adaptation to diverse learner needs. To address these issues, we propose a co llaborative multi-role a gent framework called COMA for automatic LP generation. COMA formulates LP generation as a collaborative workflow among multiple LLM agents with distinct pedagogical expertise: (1) the novice agent that represents a novice teacher possesses an overarching understanding of the intended lesson flow but demonstrates limited precision in implementing the specific instructional actions; (2) the veteran agent that represents an experienced teacher demonstrates deep familiarity with the curriculum, textbooks, and the knowledge components embedded in each unit; and (3) the master agent that represents a pedagogical expert exhibits a well-developed and confident grasp of lesson progression, with the ability to design, adapt, and implement specific instructional actions effectively and responsively. Through an iterative workflow, these agents collaboratively refine LP quality. Comprehensive experiments across five subjects, using expert-designed metrics, demonstrate that COMA significantly outperforms state-of-the-art methods, producing lesson plans with superior quality, coherence, and pedagogical alignment. Our framework offers a robust solution for generating deployable instructional content at scale. Data and code are available at https://github.com/ai4ed/COMA-LessonPlan.
Graph unlearning has emerged as a critical mechanism for supporting sustainable and privacy-preserving social networks, enabling models to remove the influence of deleted nodes and thereby better safeguard user information. However, we observe that existing graph unlearning techniques insufficiently protect sensitive attributes, often leading to degraded algorithmic fairness compared with traditional graph learning methods. To address this gap, we introduce FairGU, a fairness-aware graph unlearning framework designed to preserve both utility and fairness during the unlearning process. FairGU integrates a dedicated fairness-aware module with effective data protection strategies, ensuring that sensitive attributes are neither inadvertently amplified nor structurally exposed when nodes are removed. Through extensive experiments on multiple real-world datasets, we demonstrate that FairGU consistently outperforms state-of-the-art graph unlearning methods and fairness-enhanced graph learning baselines in terms of both accuracy and fairness metrics. Our findings highlight a previously overlooked risk in current unlearning practices and establish FairGU as a robust and equitable solution for the next generation of socially sustainable networked systems. The codes are available at https://github.com/LuoRenqiang/FairGU.
In remote or underserved regions, where road networks are often either unavailable or poorly mapped, and GPS signals are sparse and unreliable, the quality of individual trajectories is severely compromised. In such contexts, web crowdsourced data becomes essential for accurately recovering trajectories and compensating for missing spatial information in the absence of explicit road networks. However, this situation introduces two key challenges:(i) scarcity of data in unseen regions, restricting transfer learning; and (ii) the necessity to infer latent movement structures under roadless conditions. To address these, we propose Region-aware Hierarchical Trajectory Recovery (RHTR) model, designed for location inference from web crowdsourced data in sparse, roadless scenarios. RHTR constructs multi-scale implicit grid-based offset maps from historical location data, with coarse grids capturing global patterns and fine grids refining local details. These sequential representations form region-aware encodings by sampling information around observed points, facilitating trajectory recovery. A coarse-to-fine mechanism leverages contextual information to progressively reconstruct missing segments. Experiments on two public datasets—simulating underserved and disaster-like settings with cross-region transfer—demonstrate that RHTR achieves state-of-the-art performance in trajectory recovery.
Accurate forecasting of Avian Influenza Virus (AIV) outbreaks within wild bird populations necessitates models that account for complex, multi-scale transmission patterns driven by diverse factors. While conventional spatiotemporal epidemic models are robust for human-centric diseases, they rely on spatial homophily and diffusive transmission between geographic regions. This simplification is incomplete for AIV as it neglects valuable genomic information critical for capturing dynamics like high-frequency reassortment and lineage turnover at the case level (e.g., genetic descent across regions), which are essential for understanding AIV spread. To address these limitations, we systematically formulate the AIV forecasting problem and propose BLUE (bi-layer genomic-aware heterogeneous graph fusion pipeline). This pipeline integrates genetic, spatial, and ecological data to achieve highly accurate outbreak forecasting. It 1) defines a multi-layered graph structure incorporating information from diverse sources and multiple layers (case and location), 2) applies cross-relation smoothing to smooth information flow across edge types, 3) performs graph fusion that preserves critical structural patterns backed by theoretical spectral guarantees, and 4) forecasts future outbreaks using an autoregressive graph sequence model to capture transmission dynamics. To support research, we release the Avian-US dataset, which provides comprehensive genetic, spatial, and ecological data on US avian influenza outbreaks. BLUE demonstrates superior performance over existing baselines, highlighting the efficacy of integrating multi-layer information for infectious disease forecasting. The code is available at: https://github.com/cruiseresearchgroup/BLUE.