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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Jinghong, Jiang, Changlong, Li, Jiaqi, Kuang, Haohong, Xu, Hang, Yan, Tingbing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908562801819648
author Zheng, Jinghong
Jiang, Changlong
Li, Jiaqi
Kuang, Haohong
Xu, Hang
Yan, Tingbing
author_facet Zheng, Jinghong
Jiang, Changlong
Li, Jiaqi
Kuang, Haohong
Xu, Hang
Yan, Tingbing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23376
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniPose: Unified Cross-modality Pose Prior Propagation towards RGB-D data for Weakly Supervised 3D Human Pose Estimation
Zheng, Jinghong
Jiang, Changlong
Li, Jiaqi
Kuang, Haohong
Xu, Hang
Yan, Tingbing
Computer Vision and Pattern Recognition
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.
title UniPose: Unified Cross-modality Pose Prior Propagation towards RGB-D data for Weakly Supervised 3D Human Pose Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.23376