{"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/reco-region-controlled-text-to-image","title":"ReCo: Region-Controlled Text-to-Image Generation","arxiv_id":"2211.15518","date":"2022-11-23","proceeding":"CVPR 2023 1","authors":["Zhengyuan Yang","JianFeng Wang","Zhe Gan","Linjie Li","Kevin Lin","Chenfei Wu","Nan Duan","Zicheng Liu","Ce Liu","Michael Zeng","Lijuan Wang"],"abstract":"Recently, large-scale text-to-image (T2I) models have shown impressive performance in generating high-fidelity images, but with limited controllability, e.g., precisely specifying the content in a specific region with a free-form text description. In this paper, we propose an effective technique for such regional control in T2I generation. We augment T2I models' inputs with an extra set of position tokens, which represent the quantized spatial coordinates. Each region is specified by four position tokens to represent the top-left and bottom-right corners, followed by an open-ended natural language regional description. Then, we fine-tune a pre-trained T2I model with such new input interface. Our model, dubbed as ReCo (Region-Controlled T2I), enables the region control for arbitrary objects described by open-ended regional texts rather than by object labels from a constrained category set. Empirically, ReCo achieves better image quality than the T2I model strengthened by positional words (FID: 8.82->7.36, SceneFID: 15.54->6.51 on COCO), together with objects being more accurately placed, amounting to a 20.40% region classification accuracy improvement on COCO. Furthermore, we demonstrate that ReCo can better control the object count, spatial relationship, and region attributes such as color/size, with the free-form regional description. Human evaluation on PaintSkill shows that ReCo is +19.28% and +17.21% more accurate in generating images with correct object count and spatial relationship than the T2I model.","url_abs":"https://arxiv.org/abs/2211.15518v1","url_pdf":"https://arxiv.org/pdf/2211.15518v1.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":[],"tasks":[{"task_slug":"conditional-text-to-image-synthesis","task_name":"Conditional Text-to-Image Synthesis"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"layout-to-image-generation","task_name":"Layout-to-Image Generation"},{"task_slug":null,"task_name":"Position"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-text-to-image-synthesis-on-coco-1","task":"Conditional Text-to-Image Synthesis","dataset":"COCO-MIG","model":"ReCo","rank_in_archive_order":2,"of":5,"metrics":{"instance success rate":"0.55","mIoU":"0.49"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench","task":"Layout-to-Image Generation","dataset":"LayoutBench","model":"ReCo","rank_in_archive_order":3,"of":3,"metrics":{"AP":"7.6"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench-4","task":"Layout-to-Image Generation","dataset":"LayoutBench-COCO - Combination","model":"ReCo","rank_in_archive_order":3,"of":4,"metrics":{"AP":"18.7"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench-1","task":"Layout-to-Image Generation","dataset":"LayoutBench-COCO - Number","model":"ReCo","rank_in_archive_order":2,"of":4,"metrics":{"AP":"30.9"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench-2","task":"Layout-to-Image Generation","dataset":"LayoutBench-COCO - Position","model":"ReCo","rank_in_archive_order":3,"of":4,"metrics":{"AP":"36.4"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-layoutbench-3","task":"Layout-to-Image Generation","dataset":"LayoutBench-COCO - Size","model":"ReCo","rank_in_archive_order":3,"of":4,"metrics":{"AP":"24.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.15518","atlas_url":"https://app.syntology.ai/?focus=2211.15518","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":"2211.15518"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2211.15518\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2211.15518"},"call":"get_concepts_for_paper(arxiv_id=\"2211.15518\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"57b160e7456463bdd6325b7b7a7dbbb8859f5ff0abfc52235a61edf536631618","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}