{"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/object-centric-image-generation-from-layouts","title":"Object-Centric Image Generation from Layouts","arxiv_id":"2003.07449","date":"2020-03-16","proceeding":null,"authors":["Tristan Sylvain","Pengchuan Zhang","Yoshua Bengio","R. Devon Hjelm","Shikhar Sharma"],"abstract":"Despite recent impressive results on single-object and single-domain image generation, the generation of complex scenes with multiple objects remains challenging. In this paper, we start with the idea that a model must be able to understand individual objects and relationships between objects in order to generate complex scenes well. Our layout-to-image-generation method, which we call Object-Centric Generative Adversarial Network (or OC-GAN), relies on a novel Scene-Graph Similarity Module (SGSM). The SGSM learns representations of the spatial relationships between objects in the scene, which lead to our model's improved layout-fidelity. We also propose changes to the conditioning mechanism of the generator that enhance its object instance-awareness. Apart from improving image quality, our contributions mitigate two failure modes in previous approaches: (1) spurious objects being generated without corresponding bounding boxes in the layout, and (2) overlapping bounding boxes in the layout leading to merged objects in images. Extensive quantitative evaluation and ablation studies demonstrate the impact of our contributions, with our model outperforming previous state-of-the-art approaches on both the COCO-Stuff and Visual Genome datasets. Finally, we address an important limitation of evaluation metrics used in previous works by introducing SceneFID -- an object-centric adaptation of the popular Fr{\\'e}chet Inception Distance metric, that is better suited for multi-object images.","url_abs":"https://arxiv.org/abs/2003.07449v2","url_pdf":"https://arxiv.org/pdf/2003.07449v2.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":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"layout-to-image-generation","task_name":"Layout-to-Image Generation"},{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/layout-to-image-generation-on-coco-stuff-3","task":"Layout-to-Image Generation","dataset":"COCO-Stuff 128x128","model":"OC-GAN","rank_in_archive_order":4,"of":5,"metrics":{"FID":"36.31","Inception Score":"14.6","SceneFID":"16.76"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-coco-stuff-4","task":"Layout-to-Image Generation","dataset":"COCO-Stuff 256x256","model":"OC-GAN","rank_in_archive_order":3,"of":5,"metrics":{"FID":"41.65","Inception Score":"17.8"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-coco-stuff-2","task":"Layout-to-Image Generation","dataset":"COCO-Stuff 64x64","model":"OC-GAN","rank_in_archive_order":1,"of":5,"metrics":{"FID":"29.57","Inception Score":"10.8"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-visual-genome-3","task":"Layout-to-Image Generation","dataset":"Visual Genome 128x128","model":"OC-GAN","rank_in_archive_order":3,"of":5,"metrics":{"FID":"28.26","Inception Score":"12.3","SceneFID":"9.63"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-visual-genome-4","task":"Layout-to-Image Generation","dataset":"Visual Genome 256x256","model":"OC-GAN","rank_in_archive_order":4,"of":4,"metrics":{"FID":"40.85","Inception Score":"14.7"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-visual-genome-2","task":"Layout-to-Image Generation","dataset":"Visual Genome 64x64","model":"OC-GAN","rank_in_archive_order":1,"of":4,"metrics":{"FID":"20.27","Inception Score":"9.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2003.07449","atlas_url":"https://app.syntology.ai/?focus=2003.07449","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":"2003.07449"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2003.07449\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2003.07449"},"call":"get_concepts_for_paper(arxiv_id=\"2003.07449\")"}],"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":"f4dd0efb546a139dc4f1d5d203af35f3d8dc28d292dd01dd7611ae594dda21e1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}