Leveraging Temporal Joint Depths for Improving 3D Human Pose Estimation in Video
This work addresses 3D pose estimation for video analysis, but it appears incremental as it builds on existing temporal refinement approaches.
The paper tackles the problem of 3D human pose estimation in video by addressing ambiguity in joint depths from 2D poses, proposing a method to refine 3D poses using temporal information, which improves accuracy.
The effectiveness of the approaches to predict 3D poses from 2D poses estimated in each frame of a video has been demonstrated for 3D human pose estimation. However, 2D poses without appearance information of persons have much ambiguity with respect to the joint depths. In this paper, we propose to estimate a 3D pose in each frame of a video and refine it considering temporal information. The proposed approach reduces the ambiguity of the joint depths and improves the 3D pose estimation accuracy.