2021 IEEE International Conference on Image Processing
19-22 September 2021 • Anchorage, Alaska, USA
Imaging Without Borders
| Paper ID | 3D-3.9 | ||
| Paper Title | POSERN: A 2D POSE REFINEMENT NETWORK FOR BIAS-FREE MULTI-VIEW 3D HUMAN POSE ESTIMATION | ||
| Authors | Akihiko Sayo, Diego Thomas, Hiroshi Kawasaki, Kyushu University, Japan; Yuta Nakashima, Osaka University, Japan; Katsushi Ikeuchi, Microsoft, United States | ||
| Session | 3D-3: Stereoscopic and multiview processing | ||
| Location | Area J | ||
| Session Time: | Wednesday, 22 September, 14:30 - 16:00 | ||
| Presentation Time: | Wednesday, 22 September, 14:30 - 16:00 | ||
| Presentation | Poster | ||
| Topic | Three-Dimensional Image and Video Processing: Stereoscopic and multiview processing and display | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | We propose a new 2D pose refinement network that learnsto predict the human bias in the estimated 2D pose. There arebiases in 2D pose estimations that are due to differences be-tween annotations of 2D joint locations based on annotators’perception and those defined by motion capture (MoCap) sys-tems. These biases are crafted into publicly available 2D posedatasets and cannot be removed with existing error reductionapproaches. Our proposed pose refinement network allowsus to efficiently remove the human bias in the estimated 2Dposes and achieve highly accurate multi-view 3D human poseestimation. | ||