Research map / Video / Video generation
V2VFusion: Text-Controlled Video-to-Video Diffusion for Degradation-Aware Video Fusion
Jiajun Chen, Han Xu, Yunfei Huang, Zhuoya Zhang, Guangcan Liu, Jiayi Ma
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes V2VFusion, a text-controlled video-to-video diffusion model for degradation-aware video fusion that aims to unify spatio-temporal modeling across source video sequences.
Problem
Existing video fusion methods fuse frame-by-frame, lacking unified spatio-temporal modeling across sequences, which hurts temporal coherence; they also ignore temporal dynamics under degradations and overload one network with diverse degradation types.
Approach
Uses a text-controlled video-to-video diffusion formulation so that fusion is performed over whole video sequences with degradation-specific text control, rather than frame-wise fusion with a single monolithic network. Only the abstract was available, so the details of the mechanism are not confirmed.
Closest papers by meaning
- Towards Heterogeneous-Degradation-Robust Image Fusion with Controllable Generative Modulation (TPAMI 2026 · similarity 0.89)
- Degradation-Robust and Temporally Consistent Infrared–Visible Video Fusion via One-step Diffusion Framework (ECCV 2026 · similarity 0.89)
- ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts (NeurIPS 2025 · similarity 0.89)
- A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking (NeurIPS 2025 · similarity 0.88)
- FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis (CVPR 2024 · similarity 0.86)
- PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
