Abstract
Compared with depth-based 3D hand pose estimation, it is more challenging to infer 3D hand pose from monocular RGB images, due to substantial depth ambiguity and the difficulty of obtaining fully-annotated training data. Different from existing learning-based monocular RGB-input approaches that require accurate 3D annotations for training, we propose to leverage the depth images that can be easily obtained from commodity RGB-D cameras during training, while during testing we take only RGB inputs for 3D joint predictions. In this way, we alleviate the burden of the costly 3D annotations in real-world dataset. Particularly, we propose a weakly-supervised method, adaptating from fully-annotated synthetic dataset to weakly-labeled real-world dataset with the aid of a depth regularizer, which generates depth maps from predicted 3D pose and serves as weak supervision for 3D pose regression. Extensive experiments on benchmark datasets validate the effectiveness of the proposed depth regularizer in both weakly-supervised and fully-supervised settings.
Original language | English |
---|---|
Title of host publication | Computer Vision – ECCV 2018 |
Subtitle of host publication | 15th European Conference Munich, Germany, September 8–14, 2018 Proceedings, Part VI |
Editors | Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, Yair Weiss |
Place of Publication | Cham Switzerland |
Publisher | Springer |
Pages | 678-694 |
Number of pages | 17 |
ISBN (Electronic) | 9783030012311 |
ISBN (Print) | 9783030012304 |
DOIs | |
Publication status | Published - 2018 |
Externally published | Yes |
Event | European Conference on Computer Vision 2018 - Munich, Germany Duration: 8 Sept 2018 → 14 Sept 2018 Conference number: 15th https://eccv2018.org/ https://link.springer.com/book/10.1007/978-3-030-01246-5 (Proceedings) |
Publication series
Name | Lecture Notes in Computer Science |
---|---|
Publisher | Springer |
Volume | 11210 |
ISSN (Print) | 0302-9743 |
ISSN (Electronic) | 1611-3349 |
Conference
Conference | European Conference on Computer Vision 2018 |
---|---|
Abbreviated title | ECCV 2018 |
Country/Territory | Germany |
City | Munich |
Period | 8/09/18 → 14/09/18 |
Internet address |
Keywords
- 3D hand pose estimation
- Depth regularizer
- Weakly-supervised methods