# Towards Good Practices for Deep 3D Hand Pose Estimation

arXiv: https://arxiv.org/abs/1707.07248 · HTML: https://mlsanity.com/paper/1707.07248/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2017.

## Built on by (most cited first, 11 of 11)

- [DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders](https://mlsanity.com/paper/2108.08557/) (2021)
- [High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition](https://mlsanity.com/paper/2307.05541/) (2023)
- [Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wild](https://mlsanity.com/paper/2209.12009/) (2022)
- [Learning to Estimate 3D Human Pose from Point Cloud](https://mlsanity.com/paper/2212.12910/) (2022)
- [TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimation](https://mlsanity.com/paper/2206.07117/) (2022)
- [A Comprehensive Review of Sign Language Recognition: Different Types, Modalities, and Datasets](https://mlsanity.com/paper/2204.03328/) (2022)
- [Sports Analysis and VR Viewing System Based on Player Tracking and Pose Estimation with Multimodal and Multiview Sensors](https://mlsanity.com/paper/2405.01112/) (2024)
- [LiCamPose: Combining Multi-View LiDAR and RGB Cameras for Robust Single-timestamp 3D Human Pose Estimation](https://mlsanity.com/paper/2312.06409/) (2023)
- [Capsules as viewpoint learners for human pose estimation](https://mlsanity.com/paper/2302.06194/) (2023)
- [3D Pose Nowcasting: Forecast the Future to Improve the Present](https://mlsanity.com/paper/2308.12914/) (2023)
- [UniPose: Unified Cross-modality Pose Prior Propagation towards RGB-D data for Weakly Supervised 3D Human Pose Estimation](https://mlsanity.com/paper/2509.23376/) (2025)

## Abstract (arXiv)

3D hand pose estimation from single depth image is an important and challenging problem for human-computer interaction. Recently deep convolutional networks (ConvNet) with sophisticated design have been employed to address it, but the improvement over traditional random forest based methods is not so apparent. To exploit the good practice and promote the performance for hand pose estimation, we propose a tree-structured Region Ensemble Network (REN) for directly 3D coordinate regression. It first partitions the last convolution outputs of ConvNet into several grid regions. The results from separate fully-connected (FC) regressors on each regions are then integrated by another FC layer to perform the estimation. By exploitation of several training strategies including data augmentation and smooth L1 loss, proposed REN can significantly improve the performance of ConvNet to localize hand joints. The experimental results demonstrate that our approach achieves the best performance among state-of-the-art algorithms on three public hand pose datasets. We also experiment our methods on fingertip detection and human pose datasets and obtain state-of-the-art accuracy.