{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/diagnostic-benchmark-and-iterative-inpainting","title":"Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation","arxiv_id":"2304.06671","date":"2023-04-13","proceeding":null,"authors":["Jaemin Cho","Linjie Li","Zhengyuan Yang","Zhe Gan","Lijuan Wang","Mohit Bansal"],"abstract":"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","url_abs":"https://arxiv.org/abs/2304.06671v3","url_pdf":"https://arxiv.org/pdf/2304.06671v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"diagnostic-benchmark-and-iterative-inpainting","repo_url":"https://github.com/j-min/IterInpaint","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"diagnostic-benchmark-and-iterative-inpainting","repo_url":"https://github.com/j-min/LayoutBench-COCO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"layout-to-image-generation","task_name":"Layout-to-Image Generation"}],"methods":[{"method_slug":"iterinpaint","method_name":"IterInpaint"}],"datasets_introduced":[{"slug":"layoutbench","name":"LayoutBench","full_name":""},{"slug":"layoutbench-coco-combination","name":"LayoutBench-COCO - Combination","full_name":""},{"slug":"layoutbench-coco","name":"LayoutBench-COCO - Number","full_name":""},{"slug":"layoutbench-coco-position","name":"LayoutBench-COCO - Position","full_name":""},{"slug":"layoutbench-coco-size","name":"LayoutBench-COCO - Size","full_name":""}],"methods_introduced":[{"slug":"iterinpaint","name":"IterInpaint","full_name":"Iterative Inpainting"}],"results":[{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench","task":"Layout-to-Image Generation","dataset":"LayoutBench","model":"IterInpaint","rank_in_archive_order":1,"of":3,"metrics":{"AP":"36.5"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench-4","task":"Layout-to-Image Generation","dataset":"LayoutBench-COCO - Combination","model":"IterInpaint","rank_in_archive_order":1,"of":4,"metrics":{"AP":"44.1"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench-1","task":"Layout-to-Image Generation","dataset":"LayoutBench-COCO - Number","model":"IterInpaint","rank_in_archive_order":1,"of":4,"metrics":{"AP":"31.4"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench-2","task":"Layout-to-Image Generation","dataset":"LayoutBench-COCO - Position","model":"IterInpaint","rank_in_archive_order":1,"of":4,"metrics":{"AP":"39.1"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench-3","task":"Layout-to-Image Generation","dataset":"LayoutBench-COCO - Size","model":"IterInpaint","rank_in_archive_order":1,"of":4,"metrics":{"AP":"33.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.06671","atlas_url":"https://app.syntology.ai/?focus=2304.06671","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2304.06671"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2304.06671\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2304.06671"},"call":"get_concepts_for_paper(arxiv_id=\"2304.06671\")"}],"by_repo":[{"repo":"j-min/IterInpaint","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"j-min/LayoutBench-COCO","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d2ad46844779a665430dfe9a4f3cce4ff635d9ca8a018efa0c716f76e6e17c07","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}