Papers › Occlusion-Aware Networks for 3D Human Pose Estimation in Video
Occlusion-Aware Networks for 3D Human Pose Estimation in Video
Yu Cheng, Bo Yang, Bo Wang, Wending Yan, Robby T. Tan
Occlusion is a key problem in 3D human pose estimation from a monocular video. To address this problem, we introduce an occlusion-aware deep-learning framework. By employing estimated 2D confidence heatmaps of keypoints and an optical-flow consistency constraint, we filter out the unreliable estimations of occluded keypoints. When occlusion occurs, we have incomplete 2D keypoints and feed them to our 2D and 3D temporal convolutional networks (2D and 3D TCNs) that enforce temporal smoothness to produce a complete 3D pose. By using incomplete 2D keypoints, instead of complete but incorrect ones, our networks are less affected by the error-prone estimations of occluded keypoints. Training the occlusion-aware 3D TCN requires pairs of a 3D pose and a 2D pose with occlusion labels. As no such a dataset is available, we introduce a "Cylinder Man Model" to approximate the occupation of body parts in 3D space. By projecting the model onto a 2D plane in different viewing angles, we obtain and label the occluded keypoints, providing us plenty of training data. In addition, we use this model to create a pose regularization constraint, preferring the 2D estimations of unreliable keypoints to be occluded. Our method outperforms state-of-the-art methods on Human 3.6M and HumanEva-I datasets.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Human Pose Estimation | Human3.6M | Occlusion-Aware Networks | Average MPJPE (mm) | 42.9 | #26 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | Occlusion-Aware Networks | Multi-View or Monocular | Monocular | #26 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | Occlusion-Aware Networks | Using 2D ground-truth joints | No | #26 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | HumanEva-I | Occlusion-Aware Networks | Mean Reconstruction Error (mm) | 14.3 | #4 of 31 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections