Papers › Continuously Masked Transformer for Image Inpainting

Continuously Masked Transformer for Image Inpainting

1 Jan 2023ICCV 2023 1archive 2025-07-28

Keunsoo Ko, Chang-Su Kim

A novel continuous-mask-aware transformer for image inpainting, called CMT, is proposed in this paper, which uses a continuous mask to represent the amounts of errors in tokens. First, we initialize a mask and use it during the self-attention. To facilitate the masked self-attention, we also introduce the notion of overlapping tokens. Second, we update the mask by modeling the error propagation during the masked self-attention. Through several masked self-attention and mask update (MSAU) layers, we predict initial inpainting results. Finally, we refine the initial results to reconstruct a more faithful image. Experimental results on multiple datasets show that the proposed CMT algorithm outperforms existing algorithms significantly. The source codes are available at https://github.com/keunsoo-ko/CMT.

PaperPDFCode

Code

keunsoo-ko/cmt officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Inpainting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Inpainting

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