{"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/semantic-scene-completion-from-a-single-depth","title":"Semantic Scene Completion from a Single Depth Image","arxiv_id":"1611.08974","date":"2016-11-28","proceeding":"CVPR 2017 7","authors":["Shuran Song","Fisher Yu","Andy Zeng","Angel X. Chang","Manolis Savva","Thomas Funkhouser"],"abstract":"This paper focuses on semantic scene completion, a task for producing a\ncomplete 3D voxel representation of volumetric occupancy and semantic labels\nfor a scene from a single-view depth map observation. Previous work has\nconsidered scene completion and semantic labeling of depth maps separately.\nHowever, we observe that these two problems are tightly intertwined. To\nleverage the coupled nature of these two tasks, we introduce the semantic scene\ncompletion network (SSCNet), an end-to-end 3D convolutional network that takes\na single depth image as input and simultaneously outputs occupancy and semantic\nlabels for all voxels in the camera view frustum. Our network uses a\ndilation-based 3D context module to efficiently expand the receptive field and\nenable 3D context learning. To train our network, we construct SUNCG - a\nmanually created large-scale dataset of synthetic 3D scenes with dense\nvolumetric annotations. Our experiments demonstrate that the joint model\noutperforms methods addressing each task in isolation and outperforms\nalternative approaches on the semantic scene completion task.","url_abs":"http://arxiv.org/abs/1611.08974v1","url_pdf":"http://arxiv.org/pdf/1611.08974v1.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":"semantic-scene-completion-from-a-single-depth","repo_url":"https://github.com/shurans/sscnet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"semantic-scene-completion-from-a-single-depth","repo_url":"https://github.com/facebookresearch/House3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"semantic-scene-completion-from-a-single-depth","repo_url":"https://github.com/krrish94/ssc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-semantic-scene-completion","task_name":"3D Semantic Scene Completion"}],"methods":[],"datasets_introduced":[{"slug":"suncg","name":"SUNCG","full_name":"SUNCG"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-scene-completion-on-kitti-360","task":"3D Semantic Scene Completion","dataset":"KITTI-360","model":"SSCNet","rank_in_archive_order":2,"of":7,"metrics":{"mIoU":"16.95"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-scene-completion-on-nyuv2","task":"3D Semantic Scene Completion","dataset":"NYUv2","model":"SSCNet (SUNCG pretraining)","rank_in_archive_order":19,"of":28,"metrics":{"mIoU":"30.5"},"uses_additional_data":true},{"leaderboard":"/sota/3d-semantic-scene-completion-on-nyuv2","task":"3D Semantic Scene Completion","dataset":"NYUv2","model":"SSCNet","rank_in_archive_order":27,"of":28,"metrics":{"mIoU":"24.7"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-scene-completion-on-semantickitti","task":"3D Semantic Scene Completion","dataset":"SemanticKITTI","model":"SSCNet (reported in LMSCNet)","rank_in_archive_order":13,"of":20,"metrics":{"mIoU":"16.1"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-scene-completion-on-semantickitti","task":"3D Semantic Scene Completion","dataset":"SemanticKITTI","model":"SSCNet-full (reported in LMSCNet)","rank_in_archive_order":14,"of":20,"metrics":{"mIoU":"16.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.08974","atlas_url":"https://app.syntology.ai/?focus=1611.08974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.08974"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/facebookresearch/House3D","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shurans/sscnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/krrish94/ssc","reach":{"status":"ok"}}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"a49213ec2bfc8e12","entry":"vol2points","repo":"shurans/sscnet","repo_kind":"official","path":"demo/demotest_model.py","file_url":"https://github.com/shurans/sscnet/blob/HEAD/demo/demotest_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a49213ec2bfc8e12"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}