{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/holistic-3d-scene-parsing-and-reconstruction","title":"Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image","arxiv_id":"1808.02201","date":"2018-08-07","proceeding":"ECCV 2018 9","authors":["Siyuan Huang","Siyuan Qi","Yixin Zhu","Yinxue Xiao","Yuanlu Xu","Song-Chun Zhu"],"abstract":"We propose a computational framework to jointly parse a single RGB image and\nreconstruct a holistic 3D configuration composed by a set of CAD models using a\nstochastic grammar model. Specifically, we introduce a Holistic Scene Grammar\n(HSG) to represent the 3D scene structure, which characterizes a joint\ndistribution over the functional and geometric space of indoor scenes. The\nproposed HSG captures three essential and often latent dimensions of the indoor\nscenes: i) latent human context, describing the affordance and the\nfunctionality of a room arrangement, ii) geometric constraints over the scene\nconfigurations, and iii) physical constraints that guarantee physically\nplausible parsing and reconstruction. We solve this joint parsing and\nreconstruction problem in an analysis-by-synthesis fashion, seeking to minimize\nthe differences between the input image and the rendered images generated by\nour 3D representation, over the space of depth, surface normal, and object\nsegmentation map. The optimal configuration, represented by a parse graph, is\ninferred using Markov chain Monte Carlo (MCMC), which efficiently traverses\nthrough the non-differentiable solution space, jointly optimizing object\nlocalization, 3D layout, and hidden human context. Experimental results\ndemonstrate that the proposed algorithm improves the generalization ability and\nsignificantly outperforms prior methods on 3D layout estimation, 3D object\ndetection, and holistic scene understanding.","url_abs":"http://arxiv.org/abs/1808.02201v1","url_pdf":"http://arxiv.org/pdf/1808.02201v1.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":"holistic-3d-scene-parsing-and-reconstruction","repo_url":"https://github.com/thusiyuan/holistic_scene_parsing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"monocular-3d-object-detection","task_name":"Monocular 3D Object Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"room-layout-estimation","task_name":"Room Layout Estimation"},{"task_slug":"scene-parsing","task_name":"Scene Parsing"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-3d-object-detection-on-sun-rgb-d","task":"Monocular 3D Object Detection","dataset":"SUN RGB-D","model":"Holistic","rank_in_archive_order":6,"of":7,"metrics":{"AP@0.15 (10 / NYU-37)":"14.01","AP@0.15 (10 / PNet-30)":"14.01"},"uses_additional_data":false},{"leaderboard":"/sota/room-layout-estimation-on-sun-rgb-d","task":"Room Layout Estimation","dataset":"SUN RGB-D","model":"Holistic","rank_in_archive_order":6,"of":7,"metrics":{"Camera Pitch":"7.60","Camera Roll":"3.12","IoU":"54.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.02201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.02201"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thusiyuan/holistic_scene_parsing","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"adb14f1f70fdedb1","entry":"make2d","repo":"thusiyuan/holistic_scene_parsing","repo_kind":"listed","path":"utils/plyfile.py","file_url":"https://github.com/thusiyuan/holistic_scene_parsing/blob/HEAD/utils/plyfile.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"adb14f1f70fdedb1"}},{"code_sha256_prefix":"eabf66badd22efef","entry":"plot_cuboid","repo":"thusiyuan/holistic_scene_parsing","repo_kind":"listed","path":"visualize.py","file_url":"https://github.com/thusiyuan/holistic_scene_parsing/blob/HEAD/visualize.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eabf66badd22efef"}},{"code_sha256_prefix":"5d5053380b78ff19","entry":"set_logger","repo":"thusiyuan/holistic_scene_parsing","repo_kind":"listed","path":"config.py","file_url":"https://github.com/thusiyuan/holistic_scene_parsing/blob/HEAD/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d5053380b78ff19"}},{"code_sha256_prefix":"7f8010cad4b21210","entry":"show_2dboxes","repo":"thusiyuan/holistic_scene_parsing","repo_kind":"listed","path":"visualize.py","file_url":"https://github.com/thusiyuan/holistic_scene_parsing/blob/HEAD/visualize.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f8010cad4b21210"}},{"code_sha256_prefix":"aa3870a02a8d9ff8","entry":"show_2dcorner","repo":"thusiyuan/holistic_scene_parsing","repo_kind":"listed","path":"visualize.py","file_url":"https://github.com/thusiyuan/holistic_scene_parsing/blob/HEAD/visualize.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa3870a02a8d9ff8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}