{"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/language-driven-open-vocabulary-3d-scene","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","arxiv_id":"2211.16312","date":"2022-11-29","proceeding":"CVPR 2023 1","authors":["Runyu Ding","Jihan Yang","Chuhui Xue","Wenqing Zhang","Song Bai","Xiaojuan Qi"],"abstract":"Open-vocabulary scene understanding aims to localize and recognize unseen categories beyond the annotated label space. The recent breakthrough of 2D open-vocabulary perception is largely driven by Internet-scale paired image-text data with rich vocabulary concepts. However, this success cannot be directly transferred to 3D scenarios due to the inaccessibility of large-scale 3D-text pairs. To this end, we propose to distill knowledge encoded in pre-trained vision-language (VL) foundation models through captioning multi-view images from 3D, which allows explicitly associating 3D and semantic-rich captions. Further, to foster coarse-to-fine visual-semantic representation learning from captions, we design hierarchical 3D-caption pairs, leveraging geometric constraints between 3D scenes and multi-view images. Finally, by employing contrastive learning, the model learns language-aware embeddings that connect 3D and text for open-vocabulary tasks. Our method not only remarkably outperforms baseline methods by 25.8% $\\sim$ 44.7% hIoU and 14.5% $\\sim$ 50.4% hAP$_{50}$ in open-vocabulary semantic and instance segmentation, but also shows robust transferability on challenging zero-shot domain transfer tasks. See the project website at https://dingry.github.io/projects/PLA.","url_abs":"https://arxiv.org/abs/2211.16312v2","url_pdf":"https://arxiv.org/pdf/2211.16312v2.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":"language-driven-open-vocabulary-3d-scene","repo_url":"https://github.com/cvmi-lab/pla","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-open-vocabulary-instance-segmentation","task_name":"3D Open-Vocabulary Instance Segmentation"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-open-vocabulary-instance-segmentation-on-2","task":"3D Open-Vocabulary Instance Segmentation","dataset":"S3DIS","model":"PLA","rank_in_archive_order":2,"of":4,"metrics":{"AP50 Base B6/N6":"46.9","AP50 Base B8/N4 ":"59.0","AP50 Novel B6/N6":"9.8","AP50 Novel B8/N4":"8.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.16312","atlas_url":"https://app.syntology.ai/?focus=2211.16312","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}