Skip to yearly menu bar Skip to main content


Reconstructing Hands in 3D with Transformers

Georgios Pavlakos · Dandan Shan · Ilija Radosavovic · Angjoo Kanazawa · David Fouhey · Jitendra Malik

Arch 4A-E Poster #18
[ ]
Thu 20 Jun 10:30 a.m. PDT — noon PDT


We present an approach that can reconstruct hands in 3D from monocular input. Our approach for Hand Mesh Recovery, HaMeR, follows a fully transformer-based architecture and can analyze hands with significantly increased accuracy and robustness compared to previous work. The key to HaMeR’s success lies in scaling up both the data used for training and the capacity of the deep network for hand reconstruction. For training data, we combine multiple datasets that contain 2D or 3D hand annotations. For the deep model, we use a large scale Vision Transformer architecture. Our final model consistently outperforms the previous baselines on popular 3D hand pose benchmarks. To further evaluate the effect of our design in non-controlled settings, we annotate existing in-the-wild datasets with 2D hand keypoint annotations. On this newly collected dataset of annotations, HInt, we demonstrate significant improvements over existing baselines. We will make our code, data and models publicly available upon publication.

Live content is unavailable. Log in and register to view live content