# DIREG3D: DIrectly REGress 3D Hands from Multiple Cameras

arXiv: https://arxiv.org/abs/2201.11187 · HTML: https://mlsanity.com/paper/2201.11187/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 26 Jan 2022.

## Builds on (most cited first, 10 of 10)

- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.03713/) (2020)
- [3D Hand Shape and Pose from Images in the Wild](https://mlsanity.com/paper/1902.03451/) (2019)
- [Embodied Hands: Modeling and Capturing Hands and Bodies Together](https://mlsanity.com/paper/2201.02610/) (2022)
- [Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild](https://mlsanity.com/paper/2004.01946/) (2020)
- [Epipolar Transformers](https://mlsanity.com/paper/2005.04551/) (2020)
- [Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints](https://mlsanity.com/paper/2003.09282/) (2020)
- [CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth](https://mlsanity.com/paper/1904.02028/) (2019)
- [Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation](https://mlsanity.com/paper/2004.02186/) (2020)
- [Single Image 3D Hand Reconstruction with Mesh Convolutions](https://mlsanity.com/paper/1905.01326/) (2019)

## Abstract (arXiv)

In this paper, we present DIREG3D, a holistic framework for 3D Hand Tracking. The proposed framework is capable of utilizing camera intrinsic parameters, 3D geometry, intermediate 2D cues, and visual information to regress parameters for accurately representing a Hand Mesh model. Our experiments show that information like the size of the 2D hand, its distance from the optical center, and radial distortion is useful for deriving highly reliable 3D poses in camera space from just monocular information. Furthermore, we extend these results to a multi-view camera setup by fusing features from different viewpoints.