Direct Prediction of 3D Body Poses from Motion Compensated Sequences
This addresses pose estimation ambiguities in computer vision, offering a more efficient approach for applications like motion analysis, though it is incremental in method.
The paper tackles 3D human pose estimation from video by directly regressing poses from motion-compensated spatio-temporal volumes, improving state-of-the-art results on benchmarks like Human3.6m.
We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people. Previous approaches typically compute candidate poses in individual frames and then link them in a post-processing step to resolve ambiguities. By contrast, we directly regress from a spatio-temporal volume of bounding boxes to a 3D pose in the central frame. We further show that, for this approach to achieve its full potential, it is essential to compensate for the motion in consecutive frames so that the subject remains centered. This then allows us to effectively overcome ambiguities and improve upon the state-of-the-art by a large margin on the Human3.6m, HumanEva, and KTH Multiview Football 3D human pose estimation benchmarks.