{"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/3d-semantic-scene-completion-a-survey","title":"3D Semantic Scene Completion: a Survey","arxiv_id":"2103.07466","date":"2021-03-12","proceeding":null,"authors":["Luis Roldao","Raoul de Charette","Anne Verroust-Blondet"],"abstract":"Semantic Scene Completion (SSC) aims to jointly estimate the complete geometry and semantics of a scene, assuming partial sparse input. In the last years following the multiplication of large-scale 3D datasets, SSC has gained significant momentum in the research community because it holds unresolved challenges. Specifically, SSC lies in the ambiguous completion of large unobserved areas and the weak supervision signal of the ground truth. This led to a substantially increasing number of papers on the matter. This survey aims to identify, compare and analyze the techniques providing a critical analysis of the SSC literature on both methods and datasets. Throughout the paper, we provide an in-depth analysis of the existing works covering all choices made by the authors while highlighting the remaining avenues of research. SSC performance of the SoA on the most popular datasets is also evaluated and analyzed.","url_abs":"https://arxiv.org/abs/2103.07466v3","url_pdf":"https://arxiv.org/pdf/2103.07466v3.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":"3d-semantic-scene-completion","task_name":"3D Semantic Scene Completion"},{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"survey","task_name":"Survey"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-scene-completion-on-nyuv2","task":"3D Semantic Scene Completion","dataset":"NYUv2","model":"Real-time semantic scene completion via feature aggregation and conditioned prediction","rank_in_archive_order":10,"of":28,"metrics":{"mIoU":"34.4"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-scene-completion-on-nyuv2","task":"3D Semantic Scene Completion","dataset":"NYUv2","model":"EdgeNet (SUNCG pretraining)","rank_in_archive_order":12,"of":28,"metrics":{"mIoU":"33.7"},"uses_additional_data":true},{"leaderboard":"/sota/3d-semantic-scene-completion-on-nyuv2","task":"3D Semantic Scene Completion","dataset":"NYUv2","model":"VD-CRF: Semantic scene completion with dense\nCRF from a single depth image. (SUNCG pretraining)","rank_in_archive_order":16,"of":28,"metrics":{"mIoU":"31.8"},"uses_additional_data":true},{"leaderboard":"/sota/3d-semantic-scene-completion-on-nyuv2","task":"3D Semantic Scene Completion","dataset":"NYUv2","model":"Am2fnet: Attention-based multiscale\n& multi-modality fused network","rank_in_archive_order":17,"of":28,"metrics":{"mIoU":"31.7"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-scene-completion-on-nyuv2","task":"3D Semantic Scene Completion","dataset":"NYUv2","model":"3D semantic scene completion\nfrom a single depth image using adversarial training","rank_in_archive_order":28,"of":28,"metrics":{"mIoU":"22.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.07466","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}