BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918017540030464 |
|---|---|
| author | Hu, Panwen Huang, Jiehui Sun, Qiang Liang, Xiaodan |
| author_facet | Hu, Panwen Huang, Jiehui Sun, Qiang Liang, Xiaodan |
| contents | Both zero-shot and tuning-based customized text-to-image (CT2I) generation have made significant progress for storytelling content creation. In contrast, research on customized text-to-video (CT2V) generation remains relatively limited. Existing zero-shot CT2V methods suffer from poor generalization, while another line of work directly combining tuning-based T2I models with temporal motion modules often leads to the loss of structural and texture information. To bridge this gap, we propose an autoregressive structure and texture propagation module (STPM), which extracts key structural and texture features from the reference subject and injects them autoregressively into each video frame to enhance consistency. Additionally, we introduce a test-time reward optimization (TTRO) method to further refine fine-grained details. Quantitative and qualitative experiments validate the effectiveness of STPM and TTRO, demonstrating improvements of 7.8 and 13.1 in CLIP-I and DINO consistency metrics over the baseline, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_06985 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagation Hu, Panwen Huang, Jiehui Sun, Qiang Liang, Xiaodan Computer Vision and Pattern Recognition Both zero-shot and tuning-based customized text-to-image (CT2I) generation have made significant progress for storytelling content creation. In contrast, research on customized text-to-video (CT2V) generation remains relatively limited. Existing zero-shot CT2V methods suffer from poor generalization, while another line of work directly combining tuning-based T2I models with temporal motion modules often leads to the loss of structural and texture information. To bridge this gap, we propose an autoregressive structure and texture propagation module (STPM), which extracts key structural and texture features from the reference subject and injects them autoregressively into each video frame to enhance consistency. Additionally, we introduce a test-time reward optimization (TTRO) method to further refine fine-grained details. Quantitative and qualitative experiments validate the effectiveness of STPM and TTRO, demonstrating improvements of 7.8 and 13.1 in CLIP-I and DINO consistency metrics over the baseline, respectively. |
| title | BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.06985 |