View Consistency Aware Holistic Triangulation for 3D Human Pose
Estimation
- URL: http://arxiv.org/abs/2302.11301v2
- Date: Thu, 23 Feb 2023 02:01:36 GMT
- Title: View Consistency Aware Holistic Triangulation for 3D Human Pose
Estimation
- Authors: Xiaoyue Wan, Zhuo Chen, Xu Zhao
- Abstract summary: We introduce a Multi-View Fusion module to refine 2D results by establishing view correlations.
Holistic Triangulation is proposed to infer the whole pose as an entirety, and anatomy prior is injected to maintain the pose coherence.
Our method outperforms the state of the art in both precision and plausibility which is assessed by a new metric.
- Score: 19.17724401988387
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: The rapid development of multi-view 3D human pose estimation (HPE) is
attributed to the maturation of monocular 2D HPE and the geometry of 3D
reconstruction. However, 2D detection outliers in occluded views due to neglect
of view consistency, and 3D implausible poses due to lack of pose coherence,
remain challenges. To solve this, we introduce a Multi-View Fusion module to
refine 2D results by establishing view correlations. Then, Holistic
Triangulation is proposed to infer the whole pose as an entirety, and anatomy
prior is injected to maintain the pose coherence and improve the plausibility.
Anatomy prior is extracted by PCA whose input is skeletal structure features,
which can factor out global context and joint-by-joint relationship from
abstract to concrete. Benefiting from the closed-form solution, the whole
framework is trained end-to-end. Our method outperforms the state of the art in
both precision and plausibility which is assessed by a new metric.
Related papers
Err
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.