Abstract / Description of output
Although occlusion widely exists in nature and remains a fundamental challenge for pose estimation, existing heatmap-based approaches suffer serious degradation on occlusions. Their intrinsic problem is that they directly localize the joints based on visual information; however, the invisible joints are lack of that. In contrast to localization, our framework estimates the invisible joints from an inference perspective by proposing an Image-Guided Progressive GCN module which provides a comprehensive understanding of both image context and pose structure. Moreover, existing benchmarks contain limited occlusions for evaluation. Therefore, we thoroughly pursue this problem and propose a novel OPEC-Net framework together with a new Occluded Pose (OCPose) dataset with 9k annotated images. Extensive quantitative and qualitative evaluations on benchmarks demonstrate that OPEC-Net achieves significant improvements over recent leading works. Notably, our OCPose is the most complex occlusion dataset with respect to average IoU between adjacent instances. Source code and OCPose will be publicly available.
Original language | English |
---|---|
Title of host publication | Computer Vision -- ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIX |
Editors | Andrea Vedaldi, Horst Bischof, Thomas Brox, Jan-Michael Frahm |
Place of Publication | Cham |
Publisher | Springer |
Pages | 488-504 |
Number of pages | 17 |
ISBN (Electronic) | 978-3-030-58529-7 |
ISBN (Print) | 978-3-030-58528-0 |
DOIs | |
Publication status | Published - 13 Nov 2020 |
Event | 16th European Conference on Computer Vision - Virtual conference Duration: 23 Aug 2020 → 28 Aug 2020 https://eccv2020.eu/ |
Publication series
Name | Lecture Notes in Computer Science |
---|---|
Publisher | Springer Cham |
Volume | 12364 |
ISSN (Print) | 0302-9743 |
ISSN (Electronic) | 1611-3349 |
Conference
Conference | 16th European Conference on Computer Vision |
---|---|
Abbreviated title | ECCV 2020 |
City | Virtual conference |
Period | 23/08/20 → 28/08/20 |
Internet address |
Keywords / Materials (for Non-textual outputs)
- Pose estimation
- Occlusion
- Progressive GCN