1. [Publications](/index.php/publications)
2. KAMA: 3D Keypoint Aware Body Mesh Articulation

 # KAMA: 3D Keypoint Aware Body Mesh Articulation

  ![](/sites/default/files/publications/kama_0.gif)

 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.

 ## Authors

[Umar Iqbal](/index.php/person/umar-iqbal)

Kevin Xie (NVDIA)

Kelly Guo (NVIDIA)

[Jan Kautz](/index.php/person/jan-kautz)

[Pavlo Molchanov](/index.php/person/pavlo-molchanov)

 ## Publication Date

Wednesday, December 1, 2021

 ## Published in

[International Conference on 3D Vision](https://3dv2021.surrey.ac.uk/)

 ## Research Area

[Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence)

[Computer Graphics](/index.php/research-area/computer-graphics)

[Computer Vision](/index.php/research-area/computer-vision)

 ## External Links

[ArXiv](https://arxiv.org/abs/2104.13502)

 ## Uploaded Files

[kama.pdf](https://d1qx31qr3h6wln.cloudfront.net/publications/kama.pdf "Open file in new window")5.05 MB