AI Paper Atlas

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

NeurIPS 2026 · Video › Video generation · approach: Efficient video diffusion models

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy