{"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/top-down-beats-bottom-up-in-3d-instance","title":"Top-Down Beats Bottom-Up in 3D Instance Segmentation","arxiv_id":"2302.02871","date":"2023-02-06","proceeding":null,"authors":["Maksim Kolodiazhnyi","Anna Vorontsova","Anton Konushin","Danila Rukhovich"],"abstract":"Most 3D instance segmentation methods exploit a bottom-up strategy, typically including resource-exhaustive post-processing. For point grouping, bottom-up methods rely on prior assumptions about the objects in the form of hyperparameters, which are domain-specific and need to be carefully tuned. On the contrary, we address 3D instance segmentation with a TD3D: the pioneering cluster-free, fully-convolutional and entirely data-driven approach trained in an end-to-end manner. This is the first top-down method outperforming bottom-up approaches in 3D domain. With its straightforward pipeline, it demonstrates outstanding accuracy and generalization ability on the standard indoor benchmarks: ScanNet v2, its extension ScanNet200, and S3DIS, as well as on the aerial STPLS3D dataset. Besides, our method is much faster on inference than the current state-of-the-art grouping-based approaches: our flagship modification is 1.9x faster than the most accurate bottom-up method, while being more accurate, and our faster modification shows state-of-the-art accuracy running at 2.6x speed. Code is available at https://github.com/SamsungLabs/td3d .","url_abs":"https://arxiv.org/abs/2302.02871v4","url_pdf":"https://arxiv.org/pdf/2302.02871v4.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-instance-segmentation-1","task_name":"3D Instance Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-instance-segmentation-on-s3dis","task":"3D Instance Segmentation","dataset":"S3DIS","model":"TD3D","rank_in_archive_order":5,"of":21,"metrics":{"AP@50":"70.4","mAP":"58.1"},"uses_additional_data":true},{"leaderboard":"/sota/3d-instance-segmentation-on-stpls3d","task":"3D Instance Segmentation","dataset":"STPLS3D","model":"TD3D","rank_in_archive_order":3,"of":9,"metrics":{"AP":"54.3","AP50":"69.8"},"uses_additional_data":false},{"leaderboard":"/sota/3d-instance-segmentation-on-scannetv2","task":"3D Instance Segmentation","dataset":"ScanNet(v2)","model":"TD3D","rank_in_archive_order":11,"of":32,"metrics":{"mAP":"48.9","mAP @ 50":"75.1","mAP@25":"87.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.02871","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}