{"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/open3dis-open-vocabulary-3d-instance","title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","arxiv_id":"2312.10671","date":"2023-12-17","proceeding":"CVPR 2024 1","authors":["Phuc D. A. Nguyen","Tuan Duc Ngo","Evangelos Kalogerakis","Chuang Gan","Anh Tran","Cuong Pham","Khoi Nguyen"],"abstract":"We introduce Open3DIS, a novel solution designed to tackle the problem of Open-Vocabulary Instance Segmentation within 3D scenes. Objects within 3D environments exhibit diverse shapes, scales, and colors, making precise instance-level identification a challenging task. Recent advancements in Open-Vocabulary scene understanding have made significant strides in this area by employing class-agnostic 3D instance proposal networks for object localization and learning queryable features for each 3D mask. While these methods produce high-quality instance proposals, they struggle with identifying small-scale and geometrically ambiguous objects. The key idea of our method is a new module that aggregates 2D instance masks across frames and maps them to geometrically coherent point cloud regions as high-quality object proposals addressing the above limitations. These are then combined with 3D class-agnostic instance proposals to include a wide range of objects in the real world. To validate our approach, we conducted experiments on three prominent datasets, including ScanNet200, S3DIS, and Replica, demonstrating significant performance gains in segmenting objects with diverse categories over the state-of-the-art approaches.","url_abs":"https://arxiv.org/abs/2312.10671v3","url_pdf":"https://arxiv.org/pdf/2312.10671v3.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":"open3dis-open-vocabulary-3d-instance","repo_url":"https://github.com/VinAIResearch/Open3DIS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"3d-instance-segmentation-1","task_name":"3D Instance Segmentation"},{"task_slug":"3d-open-vocabulary-instance-segmentation","task_name":"3D Open-Vocabulary Instance Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":null,"task_name":"open vocabulary 3d instance segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-instance-segmentation-on-scannet-1","task":"3D Instance Segmentation","dataset":"ScanNet++","model":"Open3DIS","rank_in_archive_order":2,"of":3,"metrics":{"mAP":"20.7"},"uses_additional_data":false},{"leaderboard":"/sota/3d-instance-segmentation-on-scannet200","task":"3D Instance Segmentation","dataset":"ScanNet200","model":"Open3DIS (Open-Vocabulary)","rank_in_archive_order":5,"of":5,"metrics":{"mAP":"23.7"},"uses_additional_data":false},{"leaderboard":"/sota/3d-open-vocabulary-instance-segmentation-on-1","task":"3D Open-Vocabulary Instance Segmentation","dataset":"Replica","model":"Open3DIS","rank_in_archive_order":3,"of":7,"metrics":{"mAP":"18.1"},"uses_additional_data":false},{"leaderboard":"/sota/3d-open-vocabulary-instance-segmentation-on-2","task":"3D Open-Vocabulary Instance Segmentation","dataset":"S3DIS","model":"Open3DIS","rank_in_archive_order":1,"of":4,"metrics":{"AP50 Base B6/N6":"50.0","AP50 Base B8/N4 ":"60.8","AP50 Novel B6/N6":"29.0","AP50 Novel B8/N4":"26.3"},"uses_additional_data":false},{"leaderboard":"/sota/3d-open-vocabulary-instance-segmentation-on","task":"3D Open-Vocabulary Instance Segmentation","dataset":"ScanNet200","model":"Open3DIS","rank_in_archive_order":3,"of":6,"metrics":{"AP Common":"21.2","AP Head":"27.8","AP Tail":"21.8","AP25":"32.8","AP50":"29.4","mAP":"23.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.10671","atlas_url":"https://app.syntology.ai/?focus=2312.10671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10671"}},"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/VinAIResearch/Open3DIS","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran":8},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":0,"samples":[{"code_sha256_prefix":"f6ca0950b456bc28","entry":"NMS","repo":"VinAIResearch/Open3DIS","repo_kind":"official","path":"open3dis/src/fusion_util.py","file_url":"https://github.com/VinAIResearch/Open3DIS/blob/HEAD/open3dis/src/fusion_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f6ca0950b456bc28"}},{"code_sha256_prefix":"c58cf40ab0e3d808","entry":"adjust_intrinsic","repo":"VinAIResearch/Open3DIS","repo_kind":"official","path":"open3dis/src/fusion_util.py","file_url":"https://github.com/VinAIResearch/Open3DIS/blob/HEAD/open3dis/src/fusion_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c58cf40ab0e3d808"}},{"code_sha256_prefix":"e7b25cb2a7939cb0","entry":"eulerAnglesToRotationMatrix","repo":"VinAIResearch/Open3DIS","repo_kind":"official","path":"open3dis/dataset/arkitscenes_loader.py","file_url":"https://github.com/VinAIResearch/Open3DIS/blob/HEAD/open3dis/dataset/arkitscenes_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e7b25cb2a7939cb0"}},{"code_sha256_prefix":"067614d7fc27f768","entry":"get_grounding_output","repo":"VinAIResearch/Open3DIS","repo_kind":"official","path":"open3dis/src/grounded_sam3dv2.py","file_url":"https://github.com/VinAIResearch/Open3DIS/blob/HEAD/open3dis/src/grounded_sam3dv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"067614d7fc27f768"}},{"code_sha256_prefix":"6385efe2f5a14a24","entry":"make_intrinsic","repo":"VinAIResearch/Open3DIS","repo_kind":"official","path":"open3dis/src/fusion_util.py","file_url":"https://github.com/VinAIResearch/Open3DIS/blob/HEAD/open3dis/src/fusion_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6385efe2f5a14a24"}},{"code_sha256_prefix":"8f4499cc6f8a9ef9","entry":"rotate_pc","repo":"VinAIResearch/Open3DIS","repo_kind":"official","path":"open3dis/dataset/arkitscenes_loader.py","file_url":"https://github.com/VinAIResearch/Open3DIS/blob/HEAD/open3dis/dataset/arkitscenes_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8f4499cc6f8a9ef9"}},{"code_sha256_prefix":"339b5dd2938113e2","entry":"scaling_mapping","repo":"VinAIResearch/Open3DIS","repo_kind":"official","path":"open3dis/dataset/scannet_loader.py","file_url":"https://github.com/VinAIResearch/Open3DIS/blob/HEAD/open3dis/dataset/scannet_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"339b5dd2938113e2"}},{"code_sha256_prefix":"4d4b86c2b1c9d216","entry":"upright_camera_relative_transform","repo":"VinAIResearch/Open3DIS","repo_kind":"official","path":"open3dis/dataset/arkitscenes_loader.py","file_url":"https://github.com/VinAIResearch/Open3DIS/blob/HEAD/open3dis/dataset/arkitscenes_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4d4b86c2b1c9d216"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}