SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos
Preprint
Abstract
Markerless motion capture and understanding of professional non-daily human movements is an important yet unsolved task, which suffers from complex motion patterns and severe self-occlusion, especially for the monocular setting. In this paper, we propose SportsCap -- the first approach for simultaneously capturing 3D human motions and understanding fine-grained actions from monocular challenging sports video input. Our approach utilizes the semantic and temporally structured sub-motion prior in the embedding space for motion capture and understanding in a data-driven multi-task manner. To enable robust capture under complex motion patterns, we propose an effective motion embedding module to recover both the implicit motion embedding and explicit 3D motion details via a corresponding mapping function as well as a sub-motion classifier. Based on such hybrid motion information, we introduce a multi-stream spatial-temporal Graph Convolutional Network(ST-GCN) to predict the fine-grained semantic action attributes, and adopt a semantic attribute mapping block to assemble various correlated action attributes into a high-level action label for the overall detailed understanding of the whole sequence, so as to enable various applications like action assessment or motion scoring. Comprehensive experiments on both public and our proposed datasets show that with a challenging monocular sports video input, our novel approach not only significantly improves the accuracy of 3D human motion capture, but also recovers accurate fine-grained semantic action attributes.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- SMPL: A Skinned Multi-Person Linear Model2023
- TightCap: 3D Human Shape Capture with Clothing Tightness FieldACM Transactions on Graphics, 2021
- Graph Edge Convolutional Neural Networks for Skeleton-Based Action RecognitionIEEE Transactions on Neural Networks and Learning Systems, 2019
- OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity FieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- UnstructuredFusion: Realtime 4D Geometry and Texture Reconstruction Using Commercial RGBD CamerasIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Temporal Segment Networks for Action Recognition in VideosIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Long-Term Temporal Convolutions for Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- High-quality streamable free-viewpoint videoACM Transactions on Graphics, 2015
- Articulated pose estimation with flexible mixtures-of-parts2011
- Virtualized reality: constructing virtual worlds from real scenesIEEE MultiMedia, 1997