KAMA: 3D Keypoint Aware Body Mesh Articulation

by   Umar Iqbal, et al.

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.


page 1

page 3

page 4

page 6

page 8


HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation

Model-based 3D pose and shape estimation methods reconstruct a full 3D m...

PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images

We present PyMAF-X, a regression-based approach to recovering a full-bod...

Accurate Hand Keypoint Localization on Mobile Devices

We present a novel approach for 2D hand keypoint localization from regul...

Body Meshes as Points

We consider the challenging multi-person 3D body mesh estimation task in...

Keypoint Transfer for Fast Whole-Body Segmentation

We introduce an approach for image segmentation based on sparse correspo...

Human 3D keypoints via spatial uncertainty modeling

We introduce a technique for 3D human keypoint estimation that directly ...

Self-Supervised Keypoint Discovery in Behavioral Videos

We propose a method for learning the posture and structure of agents fro...