{"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/msta3d-multi-scale-twin-attention-for-3d-1","title":"MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation","arxiv_id":"2411.01781","date":"2024-11-04","proceeding":null,"authors":["Duc Dang Trung Tran","Byeongkeun Kang","Yeejin Lee"],"abstract":"Recently, transformer-based techniques incorporating superpoints have become prevalent in 3D instance segmentation. However, they often encounter an over-segmentation problem, especially noticeable with large objects. Additionally, unreliable mask predictions stemming from superpoint mask prediction further compound this issue. To address these challenges, we propose a novel framework called MSTA3D. It leverages multi-scale feature representation and introduces a twin-attention mechanism to effectively capture them. Furthermore, MSTA3D integrates a box query with a box regularizer, offering a complementary spatial constraint alongside semantic queries. Experimental evaluations on ScanNetV2, ScanNet200 and S3DIS datasets demonstrate that our approach surpasses state-of-the-art 3D instance segmentation methods.","url_abs":"https://arxiv.org/abs/2411.01781v3","url_pdf":"https://arxiv.org/pdf/2411.01781v3.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":"MSTA3D","rank_in_archive_order":6,"of":21,"metrics":{"AP@50":"70.0","mPrec":"80.6","mRec":"70.1"},"uses_additional_data":false},{"leaderboard":"/sota/3d-instance-segmentation-on-scannetv2","task":"3D Instance Segmentation","dataset":"ScanNet(v2)","model":"MSTA3D","rank_in_archive_order":5,"of":32,"metrics":{"mAP":"56.9","mAP @ 50":"79.5","mAP@25":"87.9","mRec":"74.1"},"uses_additional_data":false},{"leaderboard":"/sota/3d-instance-segmentation-on-scannet200","task":"3D Instance Segmentation","dataset":"ScanNet200","model":"MSTA3D","rank_in_archive_order":3,"of":5,"metrics":{"mAP":"26.2","mAP@25":"40.1","mAP@50":"35.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.01781","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}