AI RESEARCH

VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought

arXiv CS.CV

ArXi:2603.22998v1 Announce Type: new 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.