Gait Recognition via Collaborating Discriminative and Generative Diffusion Models
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_ | 1866911255881580544 |
|---|---|
| author | Xiong, Haijun Feng, Bin Wang, Bang Wang, Xinggang Liu, Wenyu |
| author_facet | Xiong, Haijun Feng, Bin Wang, Bang Wang, Xinggang Liu, Wenyu |
| contents | Gait recognition offers a non-intrusive biometric solution by identifying individuals through their walking patterns. Although discriminative models have achieved notable success in this domain, the full potential of generative models remains largely underexplored. In this paper, we introduce \textbf{CoD$^2$}, a novel framework that combines the data distribution modeling capabilities of diffusion models with the semantic representation learning strengths of discriminative models to extract robust gait features. We propose a Multi-level Conditional Control strategy that incorporates both high-level identity-aware semantic conditions and low-level visual details. Specifically, the high-level condition, extracted by the discriminative extractor, guides the generation of identity-consistent gait sequences, whereas low-level visual details, such as appearance and motion, are preserved to enhance consistency. Furthermore, the generated sequences facilitate the discriminative extractor's learning, enabling it to capture more comprehensive high-level semantic features. Extensive experiments on four datasets (SUSTech1K, CCPG, GREW, and Gait3D) demonstrate that CoD$^2$ achieves state-of-the-art performance and can be seamlessly integrated with existing discriminative methods, yielding consistent improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_06245 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Gait Recognition via Collaborating Discriminative and Generative Diffusion Models Xiong, Haijun Feng, Bin Wang, Bang Wang, Xinggang Liu, Wenyu Computer Vision and Pattern Recognition Gait recognition offers a non-intrusive biometric solution by identifying individuals through their walking patterns. Although discriminative models have achieved notable success in this domain, the full potential of generative models remains largely underexplored. In this paper, we introduce \textbf{CoD$^2$}, a novel framework that combines the data distribution modeling capabilities of diffusion models with the semantic representation learning strengths of discriminative models to extract robust gait features. We propose a Multi-level Conditional Control strategy that incorporates both high-level identity-aware semantic conditions and low-level visual details. Specifically, the high-level condition, extracted by the discriminative extractor, guides the generation of identity-consistent gait sequences, whereas low-level visual details, such as appearance and motion, are preserved to enhance consistency. Furthermore, the generated sequences facilitate the discriminative extractor's learning, enabling it to capture more comprehensive high-level semantic features. Extensive experiments on four datasets (SUSTech1K, CCPG, GREW, and Gait3D) demonstrate that CoD$^2$ achieves state-of-the-art performance and can be seamlessly integrated with existing discriminative methods, yielding consistent improvements. |
| title | Gait Recognition via Collaborating Discriminative and Generative Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.06245 |