# UniPose: Unified Cross-modality Pose Prior Propagation towards RGB-D data for Weakly Supervised 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2509.23376 · HTML: https://mlsanity.com/paper/2509.23376/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [Learning from Simulated and Unsupervised Images through Adversarial Training](https://mlsanity.com/paper/1612.07828/) (2016)
- [Panoptic Studio: A Massively Multiview System for Social Interaction Capture](https://mlsanity.com/paper/1612.03153/) (2016)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [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)
- [Self-Supervised Learning of 3D Human Pose using Multi-view Geometry](https://mlsanity.com/paper/1903.02330/) (2019)
- [PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2303.17472/) (2023)
- [RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation](https://mlsanity.com/paper/1902.09868/) (2019)
- [Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks](https://mlsanity.com/paper/1707.05740/) (2017)
- [Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation](https://mlsanity.com/paper/2004.02186/) (2020)
- [A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image](https://mlsanity.com/paper/1908.09999/) (2019)
- [Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimation](https://mlsanity.com/paper/1908.05293/) (2019)
- [Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation](https://mlsanity.com/paper/1903.08839/) (2019)
- [A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/2304.03635/) (2023)
- [Towards Good Practices for Deep 3D Hand Pose Estimation](https://mlsanity.com/paper/1707.07248/) (2017)
- [A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation](https://mlsanity.com/paper/2311.03312/) (2023)

## Abstract (arXiv)

In this paper, we present UniPose, a unified cross-modality pose prior propagation method for weakly supervised 3D human pose estimation (HPE) using unannotated single-view RGB-D sequences (RGB, depth, and point cloud data). UniPose transfers 2D HPE annotations from large-scale RGB datasets (e.g., MS COCO) to the 3D domain via self-supervised learning on easily acquired RGB-D sequences, eliminating the need for labor-intensive 3D keypoint annotations. This approach bridges the gap between 2D and 3D domains without suffering from issues related to multi-view camera calibration or synthetic-to-real data shifts. During training, UniPose leverages off-the-shelf 2D pose estimations as weak supervision for point cloud networks, incorporating spatial-temporal constraints like body symmetry and joint motion. The 2D-to-3D back-projection loss and cross-modality interaction further enhance this process. By treating the point cloud network's 3D HPE results as pseudo ground truth, our anchor-to-joint prediction method performs 3D lifting on RGB and depth networks, making it more robust against inaccuracies in 2D HPE results compared to state-of-the-art methods. Experiments on CMU Panoptic and ITOP datasets show that UniPose achieves comparable performance to fully supervised methods. Incorporating large-scale unlabeled data (e.g., NTU RGB+D 60) enhances its performance under challenging conditions, demonstrating its potential for practical applications. Our proposed 3D lifting method also achieves state-of-the-art results.