CVPR Findings2026
Consistent Video Editing as Flow-Driven Image-to-Video Generation
Ge Wang, Songlin Fan, Hangxu Liu, Quanjian Song, Hewei Wang, Jinfeng Xu
Abstract
With the prosper of video diffusion models, video editing have been significantly promoted without consuming much computational cost. One particular challenge in this task lies at the motion transfer process from the source video to the edited one, where it requires the consideration of the shape deformation in between, meanwhile maintaining the temporal consistency in the generated video sequence. However, existing methods fail to model complicated motion patterns for video editing, and are fundamentally limited to object replacement, where tasks with nonrigid object motions like multi-object and portrait editing are largely neglected. In this paper, we observe that optical flows offer a promising alternative in complex motion modeling, and present FlowV2V to re-investigate video editing as a task of flow-driven Image-to-Video (I2V) generation. Specifically, FlowV2V decomposes the entire pipeline into first-frame editing and conditional I2V generation, and simulates pseudo flow sequence that aligns with the deformed shape, thus ensuring the consistency during editing. Experimental results on DAVIS-EDIT with improvements of 13.67% and 50.66% on DOVER and warping error illustrate the superior temporal consistency and sample quality of FlowV2V compared to existing state-of-theart ones. Furthermore, we conduct comprehensive ablation studies to analyze the internal functionalities of the first-frame paradigm and flow alignment in the proposed method.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
- High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Implicit Models
- Adding Conditional Control to Text-to-Image Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
- Adding Conditional Control to Text-to-Image Diffusion Models cites Learning Transferable Visual Models From Natural Language Supervision
- ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment cites Learning Transferable Visual Models From Natural Language Supervision
- ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment cites Denoising Diffusion Implicit Models
- Denoising Diffusion Implicit Models cites Denoising Diffusion Probabilistic Models
- NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing cites High-Resolution Image Synthesis with Latent Diffusion Models
- NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing cites O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing
- NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing cites Learning Transferable Visual Models From Natural Language Supervision
- NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing cites Denoising Diffusion Probabilistic Models
Cited by top-tier papers3
- ContextFlow: Training-Free Video Object Editing via Adaptive Context EnrichmentYiyang Chen, Xuanhua He, Xiujun Ma, Jack MaAAAI 2026 · 17 citations
- O-DisCo-Edit: Object Distortion Control for Unified Realistic Video EditingYuqing Chen, Junjie Wang, Lin Liu, Ruihang Chu et al.AAAI 2026 · 6 citations
- NOVA: Sparse Control, Dense Synthesis for Pair-Free Video EditingTianlin Pan, Jiayi Dai, Chenpu Yuan, Zhengyao Lv et al.CVPR 2026 · 3 citations
Builds on23
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
Related papers
- FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video SynthesisFeng Liang, Bichen Wu, Jialiang Wang, Licheng Yu et al.CVPR 2024
- Generative Video Motion Editing with 3D Point TracksYao-Chih Lee, Zhoutong Zhang, Jiahui Huang, Jui-Hsien Wang et al.CVPR 2026 · 23 citations
- FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editingYuren Cong, Mengmeng Xu, Christian Simon, Shoufa Chen et al.ICLR 2024 · 175 citations
- MotionV2V: Editing Motion in a VideoRyan D. Burgert, Charles Herrmann, Forrester Cole, Michael S. Ryoo et al.CVPR 2026 · 13 citations
- EasyV2V: A High-quality Instruction-based Video Editing FrameworkJinjie Mai, Chaoyang Wang, Gordon Guocheng Qian, Willi Menapace et al.CVPR 2026 · 12 citations
