Conference item
MatchDiffusion: training-free generation of match-cuts
- Abstract:
- Match-cuts are powerful cinematic tools that create seamless transitions between scenes, delivering strong visual and metaphorical connections. However, crafting match-cuts is a challenging, resource-intensive process requiring deliberate artistic planning. In MatchDiffusion, we present the first training-free method for match-cut generation using textto-video diffusion models. MatchDiffusion leverages a key property of diffusion models: early denoising steps define the scene’s broad structure, while later steps add details. Guided by this insight, MatchDiffusion employs “Joint Diffusion” to initialize generation for two prompts from shared noise, aligning structure and motion. It then applies “Disjoint Diffusion”, allowing the videos to diverge and introduce unique details. This approach produces visually coherent videos suited for match-cuts. User studies and metrics demonstrate MatchDiffusion’s effectiveness and potential to democratize match-cut creation.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 4.3MB, Terms of use)
-
- Publisher copy:
- 10.1109/ICCV51701.2025.01389
Authors
- Publisher:
- IEEE
- Host title:
- 2025 IEEE/CVF International Conference on Computer Vision (ICCV)
- Pages:
- 14973-14982
- Publication date:
- 2026-04-29
- Acceptance date:
- 2025-06-25
- Event title:
- International Conference on Computer Vision (ICCV 2025)
- Event location:
- Honolulu, Hawai'i, USA
- Event website:
- https://iccv.thecvf.com/
- Event start date:
- 2025-10-19
- Event end date:
- 2025-10-23
- DOI:
- EISSN:
-
2380-7504
- ISSN:
-
1550-5499
- EISBN:
- 9798331587758
- ISBN:
- 9798331587765
- Language:
-
English
- Keywords:
- Pubs id:
-
2320857
- Local pid:
-
pubs:2320857
- Deposit date:
-
2025-11-10
- ARK identifier:
Terms of use
- Copyright holder:
- IEEE
- Copyright date:
- 2026
- Rights statement:
- ©️ IEEE 2026
- Notes:
- This paper was presented at the International Conference on Computer Vision (ICCV 2025), 19th-23rd October 2025, Honolulu, Hawai'i, USA. The author accepted manuscript (AAM) of this paper has been made available under the University of Oxford's Open Access Publications Policy, and a CC BY public copyright licence has been applied.
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record