{"total":101,"rows":[{"id":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76,"area":null},{"id":"2602.15989","title":"SAM 3D Body: Robust Full-Body Human Mesh Recovery","created":"2026-02-17","cited_by_count":69,"area":null},{"id":"2503.10625","title":"LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds","created":"2025-03-13","cited_by_count":61,"area":null},{"id":"2407.07532","title":"Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation","created":"2024-07-10","cited_by_count":59,"area":null},{"id":"2510.06219","title":"Human3R: Everyone Everywhere All at Once","created":"2025-10-07","cited_by_count":37,"area":null},{"id":"2412.02684","title":"AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction","created":"2024-12-03","cited_by_count":36,"area":null},{"id":"2501.09782","title":"SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation","created":"2025-01-16","cited_by_count":32,"area":null},{"id":"2503.14405","title":"DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers","created":"2025-03-18","cited_by_count":32,"area":"distill"},{"id":"2410.20294","title":"Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions","created":"2024-10-27","cited_by_count":31,"area":null},{"id":"2412.17806","title":"Reconstructing People, Places, and Cameras","created":"2024-12-23","cited_by_count":31,"area":null},{"id":"2410.11520","title":"Look Ma, no markers: holistic performance capture without the hassle","created":"2024-10-15","cited_by_count":23,"area":null},{"id":"2504.05303","title":"InteractVLM: 3D Interaction Reasoning from 2D Foundational Models","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2411.19824","title":"SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens","created":"2024-11-29","cited_by_count":16,"area":null},{"id":"2508.16433","title":"HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction","created":"2025-08-22","cited_by_count":15,"area":null},{"id":"2504.12186","title":"CoMotion: Concurrent Multi-person 3D Motion","created":"2025-04-16","cited_by_count":13,"area":null},{"id":"2511.03589","title":"Human Mesh Modeling for Anny Body","created":"2025-11-05","cited_by_count":10,"area":null},{"id":"2512.10881","title":"MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos","created":"2025-12-11","cited_by_count":10,"area":null},{"id":"2510.07723","title":"SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2601.01222","title":"UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass","created":"2026-01-03","cited_by_count":9,"area":null},{"id":"2607.05247","title":"Vision Pretraining for Dense Spatial Perception","created":"2026-07-06","cited_by_count":8,"area":null},{"id":"2509.24209","title":"Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2603.03265","title":"DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction","created":"2026-03-03","cited_by_count":7,"area":null},{"id":"2603.16858","title":"SOMA: Unifying Parametric Human Body Models","created":"2026-03-17","cited_by_count":6,"area":null},{"id":"2412.13058","title":"CondiMen: Conditional Multi-Person Mesh Recovery","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2506.09919","title":"MetricHMSR:Metric Human Mesh and Scene Recovery from Monocular Images","created":"2025-06-11","cited_by_count":4,"area":null},{"id":"2510.24464","title":"Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2603.15603","title":"Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2605.05207","title":"Syn4D: A Multiview Synthetic 4D Dataset","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2510.07828","title":"MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2510.21654","title":"Group Inertial Poser: Multi-Person Pose and Global Translation from Sparse Inertial Sensors and Ultra-Wideband Ranging","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2511.13282","title":"Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2511.22553","title":"Bringing Your Portrait to 3D Presence","created":"2025-11-27","cited_by_count":3,"area":null},{"id":"2601.19580","title":"QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2601.22693","title":"PEAR: Pixel-aligned Expressive humAn mesh Recovery","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2602.05755","title":"FMPose3D: monocular 3D pose estimation via flow matching","created":"2026-02-05","cited_by_count":3,"area":"diffusion"},{"id":"2603.18496","title":"NymeriaPlus: Enriching Nymeria Dataset with Additional Annotations and Data","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2607.28625","title":"ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine","created":"2026-07-30","cited_by_count":3,"area":null},{"id":"2404.10383","title":"Learning to Score Sign Language with Two-stage Method","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2409.17671","title":"Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2412.04456","title":"HeatFormer: A Neural Optimizer for Multiview Human Mesh Recovery","created":"2024-12-05","cited_by_count":2,"area":null},{"id":"2507.15212","title":"MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstruction","created":"2025-07-21","cited_by_count":2,"area":"ssm"},{"id":"2508.13562","title":"Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2508.14892","title":"Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2511.20446","title":"Learning to Generate Human-Human-Object Interactions from Textual Descriptions","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2601.16763","title":"Flow Matching for Probabilistic Monocular 3D Human Pose Estimation","created":"2026-01-23","cited_by_count":2,"area":"diffusion"},{"id":"2603.14726","title":"Enhancing Hands in 3D Whole-Body Pose Estimation with Conditional Hands Modulator","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2605.07604","title":"SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2606.14841","title":"Multi-HMR 2: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2410.00309","title":"Ask, Pose, Unite: Scaling Data Acquisition for Close Interactions with Vision Language Models","created":"2024-10-01","cited_by_count":1,"area":"mllm"},{"id":"2411.18068","title":"PersonaCraft: Personalized and Controllable Full-Body Multi-Human Scene Generation Using Occlusion-Aware 3D-Conditioned Diffusion","created":"2024-11-27","cited_by_count":1,"area":null},{"id":"2503.02916","title":"Monocular Person Localization under Camera Ego-motion","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2503.13025","title":"PoseSyn: Synthesizing Diverse 3D Pose Data from In-the-Wild 2D Data","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2504.09953","title":"Efficient 2D to Full 3D Human Pose Uplifting including Joint Rotations","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2508.00427","title":"Contact-Aware Amodal Completion for Human-Object Interaction via Multi-Regional Inpainting","created":"2025-08-01","cited_by_count":1,"area":"diffusion"},{"id":"2511.21136","title":"Efficient Training for Human Video Generation with Entropy-Guided Prioritized Progressive Learning","created":"2025-11-26","cited_by_count":1,"area":"diffusion"},{"id":"2602.19679","title":"TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2602.23951","title":"AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2604.08921","title":"TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.19673","title":"InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2604.19923","title":"UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.04728","title":"Anny-Fit: All-Age Human Mesh Recovery","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.18102","title":"DanceHMR: Hand-Aware Whole-Body Human Mesh Recovery from Monocular Videos","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.20542","title":"CalTennis: Large Multi-View Tennis Video Dataset and Benchmark of Monocular-to-3D Pose Estimation","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2607.09089","title":"DETRAM: End-to-end DEtection, Tracking and Recovery of HumAn Meshes","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2607.15868","title":"EgoExoMoCap: Distributed Ego-Exo Human Motion Capture","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2607.27616","title":"MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2505.07249","title":"When Dance Video Archives Challenge Computer Vision","created":"2025-05-12","cited_by_count":0,"area":null},{"id":"2509.04600","title":"WATCH: World-aware Allied Trajectory and pose reConstruction for Camera and Human","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2509.12197","title":"3D Human Pose and Shape Estimation from LiDAR Point Clouds: A Review","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2509.13013","title":"Dream3DAvatar: Text-Controlled 3D Avatar Reconstruction from a Single Image","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2510.12660","title":"On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2511.16673","title":"NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2512.04862","title":"Contact-Aware Refinement of Human Pose Pseudo-Ground Truth via Bioimpedance Sensing","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2512.07720","title":"ViSA: 3D-Aware Video Shading for Real-Time Upper-Body Avatar Creation","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2601.15200","title":"BBoxMaskPose v2: Expanding Mutual Conditioning to 3D","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.12789","title":"HARMONI: Aligning Human and Scene Priors for Multi-View 4D Reconstruction","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.17779","title":"CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.02799","title":"UNICA: A Unified Neural Framework for Controllable 3D Avatars","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.03814","title":"InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Dataset","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.05436","title":"Human Interaction-Aware 3D Reconstruction from a Single Image","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.12935","title":"Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.13581","title":"SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.16629","title":"Amortized Inverse Kinematics via Graph Attention for Real-Time Human Avatar Animation","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.17959","title":"Chatting about Upper-Body Expressive Human Pose and Shape Estimation","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.21712","title":"Discriminative-Generative Synergy for Occlusion Robust 3D Human Mesh Recovery","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.00271","title":"REALM: An RGB- and Event-Aligned Latent Manifold for Cross-Modal Perception","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.04554","title":"InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.13854","title":"Contrastive Multi-Modal Hypergraph Reasoning for 3D Crowd Mesh Recovery","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.25685","title":"HumanFlow -- Diffusion-Driven MAV Navigation Among Humans via Tightly-Coupled Motion Tracking, Forecasting, and Control","created":"2026-05-25","cited_by_count":0,"area":"diffusion"},{"id":"2606.20731","title":"XmoPipe: A Pipeline for Large-Scale In-the-Wild Human Motion Dataset Construction","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.01851","title":"Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction","created":"2026-07-02","cited_by_count":0,"area":"distill"},{"id":"2607.13472","title":"EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.19517","title":"Crowd4D: Scene-Aware Monocular 4D Crowd Reconstruction","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.20759","title":"DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.23850","title":"DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Models","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.00745","title":"Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.10498","title":"Field Converter: Geometry-Initialized Temporal Residual Refinement for World-Grounded Player Pose Estimation from Soccer Broadcasts","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.29106","title":"WildHSR: Metric Feed-Forward 4D People-Scene Reconstruction from a 3D Foundation Model","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.02597","title":"GRAFT: Growing Agglomerative Foundation Models via Continual Teacher Distillation","created":"2026-10-01","cited_by_count":0,"area":"distill"},{"id":"2610.19729","title":"A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":"100"}