Papers › Bridging Global Context Interactions for High-Fidelity Image Completion

Bridging Global Context Interactions for High-Fidelity Image Completion

2 Apr 2021CVPR 2022 1arXiv:2104.00845archive 2025-07-28

Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai, Dinh Phung

Bridging global context interactions correctly is important for high-fidelity image completion with large masks. Previous methods attempting this via deep or large receptive field (RF) convolutions cannot escape from the dominance of nearby interactions, which may be inferior. In this paper, we propose to treat image completion as a directionless sequence-to-sequence prediction task, and deploy a transformer to directly capture long-range dependence in the encoder. Crucially, we employ a restrictive CNN with small and non-overlapping RF for weighted token representation, which allows the transformer to explicitly model the long-range visible context relations with equal importance in all layers, without implicitly confounding neighboring tokens when larger RFs are used. To improve appearance consistency between visible and generated regions, a novel attention-aware layer (AAL) is introduced to better exploit distantly related high-frequency features. Overall, extensive experiments demonstrate superior performance compared to state-of-the-art methods on several datasets.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lyndonzheng/TFill officialmentioned in papermentioned on GitHubpytorch 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 InpaintingVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Inpainting FFHQ 512 x 512 TFill FID 3.50 #2 of 3 Archive leaderboard report
Image Inpainting Places2 TFill (20-50% free-form) FID 22.13 #12 of 14 Archive leaderboard report
Image Inpainting Places2 val TFill (20-30% free form) FID 15.2 #4 of 7 Archive leaderboard report
Image Inpainting Places2 val TFill (20-30% free form) PD 87.2 #4 of 7 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.

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