Motion Capture from Internet Videos

  title={Motion Capture from Internet Videos},
  author={Junting Dong and Qing Shuai and Y. Zhang and Xian Liu and Xiaowei Zhou and Hujun Bao},
Recent advances in image-based human pose estimation make it possible to capture 3D human motion from a single RGB video. However, the inherent depth ambiguity and self-occlusion in a single view prohibit the recovery of as high-quality motion as multi-view reconstruction. While multi-view videos are not common, the videos of a celebrity performing a specific action are usually abundant on the Internet. Even if these videos were recorded at different time instances, they would encode the same… Expand

Figures and Tables from this paper

Human Mesh Recovery from Multiple Shots
Reconstructing 3D Human Pose by Watching Humans in the Mirror
A-NeRF: Surface-free Human 3D Pose Refinement via Neural Rendering
Animatable Neural Radiance Fields for Human Body Modeling
Learning Compositional Representation for 4D Captures with Neural ODE
Learning Transferable Kinematic Dictionary for 3D Human Pose and Shape Reconstruction


Outdoor Human Motion Capture by Simultaneous Optimization of Pose and Camera Parameters
Learning 3D Human Dynamics From Video
Towards Accurate Marker-Less Human Shape and Pose Estimation over Time
  • Yinghao Huang
  • Computer Science
  • 2017 International Conference on 3D Vision (3DV)
  • 2017
Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
Monocular Total Capture: Posing Face, Body, and Hands in the Wild
Outdoor Markerless Motion Capture with Sparse Handheld Video Cameras
Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras
3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training
Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes: The Importance of Multiple Scene Constraints
Time-Contrastive Networks: Self-Supervised Learning from Video