VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908909535494144 |
|---|---|
| author | Zhang, Xuanyu Li, Weiqi Xing, Qunliang Xie, Jingfen Chen, Bin Li, Junlin Zhang, Li Zhang, Jian Zhao, Shijie |
| author_facet | Zhang, Xuanyu Li, Weiqi Xing, Qunliang Xie, Jingfen Chen, Bin Li, Junlin Zhang, Li Zhang, Jian Zhao, Shijie |
| contents | Video restoration in real-world scenarios is challenged by heterogeneous degradations, where static architectures and fixed inference pipelines often fail to generalize. Recent agent-based approaches offer dynamic decision making, yet existing video restoration agents remain limited by insufficient quality perception and inefficient search strategies. We propose VQ-Jarvis, a retrieval-augmented, all-in-one intelligent video restoration agent with sharper vision and faster thought. VQ-Jarvis is designed to accurately perceive degradations and subtle differences among paired restoration results, while efficiently discovering optimal restoration trajectories. To enable sharp vision, we construct VSR-Compare, the first large-scale video paired enhancement dataset with 20K comparison pairs covering 7 degradation types, 11 enhancement operators, and diverse content domains. Based on this dataset, we train a multiple operator judge model and a degradation perception model to guide agent decisions. To achieve fast thought, we introduce a hierarchical operator scheduling strategy that adapts to video difficulty: for easy cases, optimal restoration trajectories are retrieved in a one-step manner from a retrieval-augmented generation (RAG) library; for harder cases, a step-by-step greedy search is performed to balance efficiency and accuracy. Extensive experiments demonstrate that VQ-Jarvis consistently outperforms existing methods on complex degraded videos. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_22998 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought Zhang, Xuanyu Li, Weiqi Xing, Qunliang Xie, Jingfen Chen, Bin Li, Junlin Zhang, Li Zhang, Jian Zhao, Shijie Computer Vision and Pattern Recognition Video restoration in real-world scenarios is challenged by heterogeneous degradations, where static architectures and fixed inference pipelines often fail to generalize. Recent agent-based approaches offer dynamic decision making, yet existing video restoration agents remain limited by insufficient quality perception and inefficient search strategies. We propose VQ-Jarvis, a retrieval-augmented, all-in-one intelligent video restoration agent with sharper vision and faster thought. VQ-Jarvis is designed to accurately perceive degradations and subtle differences among paired restoration results, while efficiently discovering optimal restoration trajectories. To enable sharp vision, we construct VSR-Compare, the first large-scale video paired enhancement dataset with 20K comparison pairs covering 7 degradation types, 11 enhancement operators, and diverse content domains. Based on this dataset, we train a multiple operator judge model and a degradation perception model to guide agent decisions. To achieve fast thought, we introduce a hierarchical operator scheduling strategy that adapts to video difficulty: for easy cases, optimal restoration trajectories are retrieved in a one-step manner from a retrieval-augmented generation (RAG) library; for harder cases, a step-by-step greedy search is performed to balance efficiency and accuracy. Extensive experiments demonstrate that VQ-Jarvis consistently outperforms existing methods on complex degraded videos. |
| title | VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.22998 |