{"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/exploring-data-efficient-3d-scene","title":"Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts","arxiv_id":"2012.09165","date":"2020-12-16","proceeding":"CVPR 2021 1","authors":["Ji Hou","Benjamin Graham","Matthias Nießner","Saining Xie"],"abstract":"The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e.g. point clouds) are notoriously hard. For example, the number of scenes (e.g. indoor rooms) that can be accessed and scanned might be limited; even given sufficient data, acquiring 3D labels (e.g. instance masks) requires intensive human labor. In this paper, we explore data-efficient learning for 3D point cloud. As a first step towards this direction, we propose Contrastive Scene Contexts, a 3D pre-training method that makes use of both point-level correspondences and spatial contexts in a scene. Our method achieves state-of-the-art results on a suite of benchmarks where training data or labels are scarce. Our study reveals that exhaustive labelling of 3D point clouds might be unnecessary; and remarkably, on ScanNet, even using 0.1% of point labels, we still achieve 89% (instance segmentation) and 96% (semantic segmentation) of the baseline performance that uses full annotations.","url_abs":"https://arxiv.org/abs/2012.09165v3","url_pdf":"https://arxiv.org/pdf/2012.09165v3.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":"exploring-data-efficient-3d-scene","repo_url":"https://github.com/facebookresearch/ContrastiveSceneContexts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"exploring-data-efficient-3d-scene","repo_url":"https://github.com/Pointcept/Pointcept","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-scannet200","task":"3D Semantic Segmentation","dataset":"ScanNet200","model":"CSC","rank_in_archive_order":15,"of":16,"metrics":{"test mIoU":"24.9","val mIoU":"26.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"CSC+MinkUNet","rank_in_archive_order":23,"of":61,"metrics":{"mIoU":"72.2"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.09165","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}