Papers › MAT: Mask-Aware Transformer for Large Hole Image Inpainting
MAT: Mask-Aware Transformer for Large Hole Image Inpainting
Wenbo Li, Zhe Lin, Kun Zhou, Lu Qi, Yi Wang, Jiaya Jia
Recent studies have shown the importance of modeling long-range interactions in the inpainting problem. To achieve this goal, existing approaches exploit either standalone attention techniques or transformers, but usually under a low resolution in consideration of computational cost. In this paper, we present a novel transformer-based model for large hole inpainting, which unifies the merits of transformers and convolutions to efficiently process high-resolution images. We carefully design each component of our framework to guarantee the high fidelity and diversity of recovered images. Specifically, we customize an inpainting-oriented transformer block, where the attention module aggregates non-local information only from partial valid tokens, indicated by a dynamic mask. Extensive experiments demonstrate the state-of-the-art performance of the new model on multiple benchmark datasets. Code is released at https://github.com/fenglinglwb/MAT.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2203.15270", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2203.15270")
Code
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
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Inpainting | CelebA-HQ | MAT | FID | 4.86 | #1 of 6 | Archive leaderboard | report |
| Image Inpainting | CelebA-HQ | MAT | P-IDS | 13.83 | #1 of 6 | Archive leaderboard | report |
| Image Inpainting | CelebA-HQ | MAT | U-IDS | 25.33 | #1 of 6 | Archive leaderboard | report |
| Image Inpainting | Places2 | MAT | FID | 1.96 | #3 of 14 | Archive leaderboard | report |
| Image Inpainting | Places2 | MAT | P-IDS | 23.42 | #3 of 14 | Archive leaderboard | report |
| Image Inpainting | Places2 | MAT | U-IDS | 38.34 | #3 of 14 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
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