{"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/monoscene-monocular-3d-semantic-scene","title":"MonoScene: Monocular 3D Semantic Scene Completion","arxiv_id":"2112.00726","date":"2021-12-01","proceeding":"CVPR 2022 1","authors":["Anh-Quan Cao","Raoul de Charette"],"abstract":"MonoScene proposes a 3D Semantic Scene Completion (SSC) framework, where the dense geometry and semantics of a scene are inferred from a single monocular RGB image. Different from the SSC literature, relying on 2.5 or 3D input, we solve the complex problem of 2D to 3D scene reconstruction while jointly inferring its semantics. Our framework relies on successive 2D and 3D UNets bridged by a novel 2D-3D features projection inspiring from optics and introduces a 3D context relation prior to enforce spatio-semantic consistency. Along with architectural contributions, we introduce novel global scene and local frustums losses. Experiments show we outperform the literature on all metrics and datasets while hallucinating plausible scenery even beyond the camera field of view. Our code and trained models are available at https://github.com/cv-rits/MonoScene.","url_abs":"https://arxiv.org/abs/2112.00726v2","url_pdf":"https://arxiv.org/pdf/2112.00726v2.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":"monoscene-monocular-3d-semantic-scene","repo_url":"https://github.com/cv-rits/MonoScene","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"monoscene-monocular-3d-semantic-scene","repo_url":"https://github.com/astra-vision/monoscene","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"3d-scene-reconstruction","task_name":"3D Scene Reconstruction"},{"task_slug":"3d-semantic-scene-completion","task_name":"3D Semantic Scene Completion"},{"task_slug":"3d-semantic-scene-completion-from-a-single","task_name":"3D Semantic Scene Completion from a single RGB image"},{"task_slug":"single-view-3d-reconstruction","task_name":"Single-View 3D Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-scene-completion-on-kitti-360","task":"3D Semantic Scene Completion","dataset":"KITTI-360","model":"MonoScene","rank_in_archive_order":6,"of":7,"metrics":{"mIoU":"12.31"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-scene-completion-on-nyuv2","task":"3D Semantic Scene Completion","dataset":"NYUv2","model":"MonoScene (RGB input only)","rank_in_archive_order":25,"of":28,"metrics":{"mIoU":"26.94"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-scene-completion-on-semantickitti","task":"3D Semantic Scene Completion","dataset":"SemanticKITTI","model":"MonoScene (RGB input only)","rank_in_archive_order":18,"of":20,"metrics":{"mIoU":"11.08"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-scene-completion-from-a-single-2","task":"3D Semantic Scene Completion from a single RGB image","dataset":"KITTI-360","model":"MonoScene","rank_in_archive_order":3,"of":4,"metrics":{"mIoU":"12.31"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-scene-completion-from-a-single","task":"3D Semantic Scene Completion from a single RGB image","dataset":"NYUv2","model":"MonoScene","rank_in_archive_order":3,"of":6,"metrics":{"mIoU":"26.94"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-scene-completion-from-a-single-1","task":"3D Semantic Scene Completion from a single RGB image","dataset":"SemanticKITTI","model":"MonoScene","rank_in_archive_order":6,"of":9,"metrics":{"mIoU":"11.08"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2112.00726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.00726"}},"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/cv-rits/MonoScene","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/astra-vision/monoscene","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"listed":{"samples":6,"ran":3,"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":"5530781a69d17464","entry":"compute_super_CP_multilabel_loss","repo":"astra-vision/monoscene","repo_kind":"listed","path":"monoscene/loss/CRP_loss.py","file_url":"https://github.com/astra-vision/monoscene/blob/HEAD/monoscene/loss/CRP_loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5530781a69d17464"}},{"code_sha256_prefix":"251f4945130ffbc3","entry":"get_iou","repo":"astra-vision/monoscene","repo_kind":"listed","path":"monoscene/loss/sscMetrics.py","file_url":"https://github.com/astra-vision/monoscene/blob/HEAD/monoscene/loss/sscMetrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"251f4945130ffbc3"}},{"code_sha256_prefix":"d062b8e225df0d31","entry":"sem_scal_loss","repo":"astra-vision/monoscene","repo_kind":"listed","path":"monoscene/loss/ssc_loss.py","file_url":"https://github.com/astra-vision/monoscene/blob/HEAD/monoscene/loss/ssc_loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d062b8e225df0d31"}},{"code_sha256_prefix":"033da7a511cc1166","entry":"KL_sep","repo":"astra-vision/monoscene","repo_kind":"listed","path":"monoscene/loss/ssc_loss.py","file_url":"https://github.com/astra-vision/monoscene/blob/HEAD/monoscene/loss/ssc_loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"033da7a511cc1166"}},{"code_sha256_prefix":"1cf8e8cd991e96bb","entry":"geo_scal_loss","repo":"astra-vision/monoscene","repo_kind":"listed","path":"monoscene/loss/ssc_loss.py","file_url":"https://github.com/astra-vision/monoscene/blob/HEAD/monoscene/loss/ssc_loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1cf8e8cd991e96bb"}},{"code_sha256_prefix":"40d8d0dfd5686afe","entry":"get_accuracy","repo":"astra-vision/monoscene","repo_kind":"listed","path":"monoscene/loss/sscMetrics.py","file_url":"https://github.com/astra-vision/monoscene/blob/HEAD/monoscene/loss/sscMetrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"40d8d0dfd5686afe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}