We present KAMA, a 3D Keypoint Aware Mesh Articulation approach that allows us to estimate a human body mesh from the positions of 3D body keypoints. To this end, we learn to estimate 3D positions of 26 body keypoints and propose an analytical solution to articulate a parametric body model, SMPL, via a set of straightforward geometric transformations. Since keypoint estimation directly relies on image clues, our approach offers significantly better alignment to image content when compared to state-of-the-art approaches. Our proposed approach does not require any paired mesh annotations and is able to achieve state-of-the-art mesh fittings through 3D keypoint regression only. Results on the challenging 3DPW and Human3.6M demonstrate that our approach yields state-of-the-art body mesh fittings.
Cite
@article{arxiv.2104.13502,
title = {KAMA: 3D Keypoint Aware Body Mesh Articulation},
author = {Umar Iqbal and Kevin Xie and Yunrong Guo and Jan Kautz and Pavlo Molchanov},
journal= {arXiv preprint arXiv:2104.13502},
year = {2021}
}