Methods › Computer Vision › Generative Video Models › FuseFormer
FuseFormer
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
FuseFormer is a Transformer-based model designed for video inpainting via fine-grained feature fusion based on novel Soft Split and Soft Composition operations. The soft split divides feature map into many patches with given overlapping interval while the soft composition stitches them back into a whole feature map where pixels in overlapping regions are summed up. FuseFormer builds soft composition and soft split into its feedforward network for further enhancing subpatch level feature fusion.
Papers archive 2025-07-28
1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting 7 Sep 2021 · 1 repository · arXiv:2109.02974Syntology ran 10 of 11 samples · 1 unverified · 11 pointer-only (licence)
Tasks archive 2025-07-28
2 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Seeing Beyond the Visible | 1 |
| Video Inpainting | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections