Markerless Motion Capture

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 40

All topics

MotionGRPO: Overcoming Low Intra-Group Diversity in GRPO-Based Egocentric Motion Recovery
May 7, 2026Nanjie Yao, Junlong Ren, Wenhao Shen +1Diffusion Model Guidance Markerless Motion Capture
The Hong Kong University of Science and Technology (Guangzhou), China · Nanyang Technological University, Singapore
MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons
Apr 30, 2026Kehong Gong, Zhengyu Wen, Dao Thien Phong +10Markerless Motion Capture 3D Human Pose Estimation
Huawei Technologies Co., Ltd, Singapore · Huawei Central Research Institute, Singapore
Integrated Real-Time Motion Tracking and AI Analysis for Athletic Performance Optimization
Apr 23, 2026Parth Agrawal, Ronit, Sagar Kumar +1Markerless Motion Capture Sports Video Analysis
Department of Computer Science and Engineering, Chandigarh University Punjab, India
AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion
Apr 20, 2026Hongjie Li, Heng Yu, Jiaman Li +4Markerless Motion Capture 3D Reconstruction
Stanford University · H. Li is now with Peking University
CPU Optimization of a Monocular 3D Biomechanics Pipeline for Low-Resource Deployment
Apr 17, 2026Yan Zhang, Xiong ZhaoMarkerless Motion Capture Inference-Time Optimization
Google LLC · Mountain View, California, USA · AccMov Health Inc. +1
MorphGS: Morphology-Adaptive Articulated 3D Motion Transfer from Videos
Jan 6, 2026Taeyeon Kim, Youngju Na, Jumin Lee +3Markerless Motion Capture Motion Retargeting
KAIST, Republic of Korea
MonoMSK: Monocular 3D Musculoskeletal Dynamics Estimation
Nov 24, 2025Farnoosh Koleini, Hongfei Xue, Ahmed Helmy +1Markerless Motion Capture 3D Human Pose Estimation
University of North Carolina at Charlotte
TrackStudio: An Integrated Toolkit for Markerless Tracking
Nov 10, 2025Hristo Dimitrov, Viktorija Pavalkyte, Giulia Dominijanni +1Markerless Motion Capture 3D Hand Pose Estimation
1MRC Cognition and Brain Sciences Unit, University of Cambridge · Center for Neuroprosthetics and School of Engineering, ´Ecole Polytechnique F´ed´erale de Lausanne
Joint Optimization for 4D Human-Scene Reconstruction in the Wild
Jan 4, 2025Zhizheng Liu, Joe Lin, Wayne Wu +1Markerless Motion Capture 4D Reconstruction
Department of Computer Science, University of California, Los Angeles
Multi-view Hand Reconstruction with a Point-Embedded Transformer
Aug 20, 2024Lixin Yang, Licheng Zhong, Pengxiang Zhu +43D ViTs Markerless Motion Capture
School of Artificial Intelligence (SAI), Shanghai Jiao Tong University, Shanghai 200230, China · School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China · School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China +1

May 7, 2026, cs.CVJ/K move · Enter open · S save

MotionGRPO: Overcoming Low Intra-Group Diversity in GRPO-Based Egocentric Motion Recovery

Nanjie Yao, Junlong Ren, Wenhao Shen, Hao Wang

The Hong Kong University of Science and Technology (Guangzhou), China · Nanyang Technological University, Singapore

Diffusion Model Guidance Markerless Motion Capture Group Relative Policy Optimization RL for Diffusion Models

Open paper AskPDF arXiv

This paper studies full-body 3D human motion recovery from head-mounted device signals. Existing diffusion-based methods often rely on global distribution matching, leading to local joint reconstruction errors. We propose MotionGRPO, a novel framework leveraging reinforcement learning post-training to inject fine-grained guidance into the diffusion process. Technically, we model diffusion sampling as a Markov decision process optimized via Group Relative Policy Optimization (GRPO). To this end, we introduce a hybrid reward mechanism that combines a learned conditioned perceptual model for global visual plausibility and explicit constraints for local joint precision. Our key technical insight is that policy optimization in diffusion-based recovery suffers from vanishing gradients due to limited intra-group sample diversity. To address this, we further introduce a noise-injection strategy that explicitly increases sample variance and stabilizes learning. Extensive experiments demonstrate that MotionGRPO achieves state-of-the-art performance with superior visual fidelity

Momentum

Related topics

Latest papers 40