Learning to Regress Bodies from Images using Differentiable Semantic Rendering

Sai Kumar Dwivedi, Nikos Athanasiou, Muhammed Kocabas +1

Learning to regress 3D human body shape and pose (e.g.~SMPL parameters) from monocular images typically exploits losses on 2D keypoints, silhouettes, and/or part-segmentation when…