Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911172716920832 |
|---|---|
| author | Liu, Jingjing Wang, Zhiyong Fan, Xinyu Dadashzadeh, Amirhossein Liu, Honghai Mirmehdi, Majid |
| author_facet | Liu, Jingjing Wang, Zhiyong Fan, Xinyu Dadashzadeh, Amirhossein Liu, Honghai Mirmehdi, Majid |
| contents | Existing 3D human pose estimation methods often suffer in performance, when applied to cross-scenario inference, due to domain shifts in characteristics such as camera viewpoint, position, posture, and body size. Among these factors, camera viewpoints and locations have been shown to contribute significantly to the domain gap by influencing the global positions of human poses. To address this, we propose a novel framework that explicitly conducts global transformations between pose positions in the camera coordinate systems of source and target domains. We start with a Pseudo-Label Generation Module that is applied to the 2D poses of the target dataset to generate pseudo-3D poses. Then, a Global Transformation Module leverages a human-centered coordinate system as a novel bridging mechanism to seamlessly align the positional orientations of poses across disparate domains, ensuring consistent spatial referencing. To further enhance generalization, a Pose Augmentor is incorporated to address variations in human posture and body size. This process is iterative, allowing refined pseudo-labels to progressively improve guidance for domain adaptation. Our method is evaluated on various cross-dataset benchmarks, including Human3.6M, MPI-INF-3DHP, and 3DPW. The proposed method outperforms state-of-the-art approaches and even outperforms the target-trained model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_12699 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms Liu, Jingjing Wang, Zhiyong Fan, Xinyu Dadashzadeh, Amirhossein Liu, Honghai Mirmehdi, Majid Computer Vision and Pattern Recognition Existing 3D human pose estimation methods often suffer in performance, when applied to cross-scenario inference, due to domain shifts in characteristics such as camera viewpoint, position, posture, and body size. Among these factors, camera viewpoints and locations have been shown to contribute significantly to the domain gap by influencing the global positions of human poses. To address this, we propose a novel framework that explicitly conducts global transformations between pose positions in the camera coordinate systems of source and target domains. We start with a Pseudo-Label Generation Module that is applied to the 2D poses of the target dataset to generate pseudo-3D poses. Then, a Global Transformation Module leverages a human-centered coordinate system as a novel bridging mechanism to seamlessly align the positional orientations of poses across disparate domains, ensuring consistent spatial referencing. To further enhance generalization, a Pose Augmentor is incorporated to address variations in human posture and body size. This process is iterative, allowing refined pseudo-labels to progressively improve guidance for domain adaptation. Our method is evaluated on various cross-dataset benchmarks, including Human3.6M, MPI-INF-3DHP, and 3DPW. The proposed method outperforms state-of-the-art approaches and even outperforms the target-trained model. |
| title | Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.12699 |