Occlusion Resilient 3D Human Pose Estimation

arXiv:2402.11036v1 Announce Type: cross
Abstract: Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences. Temporal consistency has been extensively used to mitigate their impact but the existing algorithms in the literature do not explicitly model them.
Here, we apply this by representing the deforming body as a spatio-temporal graph. We then introduce a refinement network that performs graph convolutions over this graph to output 3D poses. To ensure robustness to occlusions, we train …

abstract algorithms apply arxiv challenges cs.cv cs.lg human impact key literature resilient temporal the key them type video