Papers › Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation

Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation

13 Apr 2023arXiv:2304.06671archive 2025-07-28

Jaemin Cho, Linjie Li, Zhengyuan Yang, Zhe Gan, Lijuan Wang, Mohit Bansal

Spatial control is a core capability in controllable image generation. Advancements in layout-guided image generation have shown promising results on in-distribution (ID) datasets with similar spatial configurations. However, it is unclear how these models perform when facing out-of-distribution (OOD) samples with arbitrary, unseen layouts. In this paper, we propose LayoutBench, a diagnostic benchmark for layout-guided image generation that examines four categories of spatial control skills: number, position, size, and shape. We benchmark two recent representative layout-guided image generation methods and observe that the good ID layout control may not generalize well to arbitrary layouts in the wild (e.g., objects at the boundary). Next, we propose IterInpaint, a new baseline that generates foreground and background regions step-by-step via inpainting, demonstrating stronger generalizability than existing models on OOD layouts in LayoutBench. We perform quantitative and qualitative evaluation and fine-grained analysis on the four LayoutBench skills to pinpoint the weaknesses of existing models. We show comprehensive ablation studies on IterInpaint, including training task ratio, crop&paste vs. repaint, and generation order. Lastly, we evaluate the zero-shot performance of different pretrained layout-guided image generation models on LayoutBench-COCO, our new benchmark for OOD layouts with real objects, where our IterInpaint consistently outperforms SOTA baselines in all four splits. Project website: https://layoutbench.github.io

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

j-min/IterInpaint officialmentioned on GitHubpytorch report
j-min/LayoutBench-COCO mentioned 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

DiagnosticImage GenerationLayout-to-Image Generation

Datasets

Introduced by this paper, per the archive.

LayoutBenchLayoutBench-COCO - CombinationLayoutBench-COCO - NumberLayoutBench-COCO - PositionLayoutBench-COCO - Size

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Layout-to-Image Generation LayoutBench IterInpaint AP 36.5 #1 of 3 Archive leaderboard report
Layout-to-Image Generation LayoutBench-COCO - Combination IterInpaint AP 44.1 #1 of 4 Archive leaderboard report
Layout-to-Image Generation LayoutBench-COCO - Number IterInpaint AP 31.4 #1 of 4 Archive leaderboard report
Layout-to-Image Generation LayoutBench-COCO - Position IterInpaint AP 39.1 #1 of 4 Archive leaderboard report
Layout-to-Image Generation LayoutBench-COCO - Size IterInpaint AP 33.5 #1 of 4 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

Introduced by this paper: IterInpaint

IterInpaint

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