# DOR3D-Net: Dense Ordinal Regression Network for 3D Hand Pose Estimation

arXiv: https://arxiv.org/abs/2403.13405 · HTML: https://mlsanity.com/paper/2403.13405/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 20 Mar 2024.

## Builds on (most cited first, 24 of 24)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [End-to-End Human Pose and Mesh Reconstruction with Transformers](https://mlsanity.com/paper/2012.09760/) (2020)
- [First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations](https://mlsanity.com/paper/1704.02463/) (2017)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild](https://mlsanity.com/paper/2004.01946/) (2020)
- [Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering](https://mlsanity.com/paper/1904.04196/) (2019)
- [Ordinal Depth Supervision for 3D Human Pose Estimation](https://mlsanity.com/paper/1805.04095/) (2018)
- [V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map](https://mlsanity.com/paper/1711.07399/) (2017)
- [Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation](https://mlsanity.com/paper/2303.11579/) (2023)
- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image](https://mlsanity.com/paper/1908.09999/) (2019)
- [HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation](https://mlsanity.com/paper/1910.12032/) (2019)
- [BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysis](https://mlsanity.com/paper/1704.02612/) (2017)
- [Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving](https://mlsanity.com/paper/2112.12141/) (2021)
- [HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving](https://mlsanity.com/paper/2212.07729/) (2022)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image](https://mlsanity.com/paper/2007.04646/) (2020)
- [DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation](https://mlsanity.com/paper/1708.08325/) (2017)
- [Dense 3D Regression for Hand Pose Estimation](https://mlsanity.com/paper/1711.08996/) (2017)
- [HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeleton](https://mlsanity.com/paper/2108.05545/) (2021)
- [Pose Guided Structured Region Ensemble Network for Cascaded Hand Pose Estimation](https://mlsanity.com/paper/1708.03416/) (2017)
- [TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimation](https://mlsanity.com/paper/2206.07117/) (2022)

## Abstract (arXiv)

Depth-based 3D hand pose estimation is an important but challenging research task in human-machine interaction community. Recently, dense regression methods have attracted increasing attention in 3D hand pose estimation task, which provide a low computational burden and high accuracy regression way by densely regressing hand joint offset maps. However, large-scale regression offset values are often affected by noise and outliers, leading to a significant drop in accuracy. To tackle this, we re-formulate 3D hand pose estimation as a dense ordinal regression problem and propose a novel Dense Ordinal Regression 3D Pose Network (DOR3D-Net). Specifically, we first decompose offset value regression into sub-tasks of binary classifications with ordinal constraints. Then, each binary classifier can predict the probability of a binary spatial relationship relative to joint, which is easier to train and yield much lower level of noise. The estimated hand joint positions are inferred by aggregating the ordinal regression results at local positions with a weighted sum. Furthermore, both joint regression loss and ordinal regression loss are used to train our DOR3D-Net in an end-to-end manner. Extensive experiments on public datasets (ICVL, MSRA, NYU and HANDS2017) show that our design provides significant improvements over SOTA methods.