KAMA: 3D Keypoint Aware Body Mesh Articulation

TL;DR

KAMA is a novel method that estimates detailed 3D human body meshes from keypoint positions, achieving superior alignment and state-of-the-art results without needing paired mesh annotations.

Contribution

It introduces a new approach combining 3D keypoint regression with an analytical solution for mesh articulation, eliminating the need for paired mesh annotations.

Findings

Achieves state-of-the-art mesh fitting on 3DPW and Human3.6M datasets.

Provides better image content alignment compared to previous methods.

Does not require paired mesh annotations for training.

Abstract

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.