RFDM: Residual Flow Diffusion Models for Video Editing

Mohammadreza Salehi; Mehdi Noroozi; Luca Morreale; Ruchika Chavhan; Malcolm Chadwick; Alberto Gil Couto Pimentel Ramos; Abhinav Mehrotra

CVPR2026顶会

RFDM: Residual Flow Diffusion Models for Video Editing

Mohammadreza Salehi, Mehdi Noroozi, Luca Morreale, Ruchika Chavhan, Malcolm Chadwick, Alberto Gil Couto Pimentel Ramos, Abhinav Mehrotra

出版方

2026年份

摘要

Figure 1. Video style transfer. Editing video style requires understanding of motion and style across frames. Naive Image-to-Image(I2I) [34] models generate inconsistent video frames. Fairy [44] smoothens the result, trading computational cost to achieve lower jittering and inconsistency. RFDM results in the most consistent edit, while being computationally similar to the per-frame baseline (I2I).

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式，引用它的顶会 Paper 也一样。你提问，回答直接引用原文。

核心论断
横向对比
局限

你的问题

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始，无需绑卡

它引用的顶会 Paper31

High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
Scaling Rectified Flow Transformers for High-Resolution Image SynthesisPatrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari 等ICML 2024 · 被引用 3,620 次
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video GenerationJay Zhangjie Wu, Yixiao Ge, Xintao Wang, Stan Weixian Lei 等ICCV 2023 · 被引用 1,113 次
Diffusion Forcing: Next-token Prediction Meets Full-Sequence DiffusionBoyuan Chen, Diego Marti Monso, Yilun Du, Max Simchowitz 等NeurIPS 2024 · 被引用 751 次
ResShift: Efficient Diffusion Model for Image Super-resolution by Residual ShiftingZongsheng Yue, Jianyi Wang, Chen Change LoyNeurIPS 2023 · 被引用 646 次

摘要

问问这篇 Paper

智能体会读完全文。

它引用的顶会 Paper31

相关 Paper