A Spatial-temporal 3D Human Pose Reconstruction Framework
This work addresses the problem of generating smoother and more natural 3D pose sequences for applications like motion capture and animation, though it appears incremental as it builds on existing methods with specific enhancements.
The paper tackles 3D human pose reconstruction from single-view camera by introducing a spatial-temporal framework that leverages intra and inter frame relationships, resulting in 10% lower Euclidean reconstruction error and improved robustness against noise compared to recent works.
3D human pose reconstruction from single-view camera is a difficult and challenging topic. Many approaches have been proposed, but almost focusing on frame-by-frame independently while inter-frames are highly correlated in a pose sequence. In contrast, we introduce a novel spatial-temporal 3D reconstruction framework that leverages both intra and inter frame relationships in consecutive 2D pose sequences. Orthogonal Matching Pursuit (OMP) algorithm, pre-trained Pose-angle Limits and Temporal Models have been implemented. We quantitatively compare our framework versus recent works on CMU motion capture dataset and Vietnamese traditional dance sequences. Our method outperforms others with 10 percent lower of Euclidean reconstruction error and robustness against Gaussian noise. Additionally, it is also important to mention that our reconstructed 3D pose sequences are smoother and more natural than others.