{"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/partslip-low-shot-part-segmentation-for-3d","title":"PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models","arxiv_id":"2212.01558","date":"2022-12-03","proceeding":"CVPR 2023 1","authors":["Minghua Liu","Yinhao Zhu","Hong Cai","Shizhong Han","Zhan Ling","Fatih Porikli","Hao Su"],"abstract":"Generalizable 3D part segmentation is important but challenging in vision and robotics. Training deep models via conventional supervised methods requires large-scale 3D datasets with fine-grained part annotations, which are costly to collect. This paper explores an alternative way for low-shot part segmentation of 3D point clouds by leveraging a pretrained image-language model, GLIP, which achieves superior performance on open-vocabulary 2D detection. We transfer the rich knowledge from 2D to 3D through GLIP-based part detection on point cloud rendering and a novel 2D-to-3D label lifting algorithm. We also utilize multi-view 3D priors and few-shot prompt tuning to boost performance significantly. Extensive evaluation on PartNet and PartNet-Mobility datasets shows that our method enables excellent zero-shot 3D part segmentation. Our few-shot version not only outperforms existing few-shot approaches by a large margin but also achieves highly competitive results compared to the fully supervised counterpart. Furthermore, we demonstrate that our method can be directly applied to iPhone-scanned point clouds without significant domain gaps.","url_abs":"https://arxiv.org/abs/2212.01558v2","url_pdf":"https://arxiv.org/pdf/2212.01558v2.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":"partslip-low-shot-part-segmentation-for-3d","repo_url":"https://github.com/Colin97/PartSLIP_page","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"partslip-low-shot-part-segmentation-for-3d","repo_url":"https://github.com/amrinkareem/paris3d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.01558","atlas_url":"https://app.syntology.ai/?focus=2212.01558","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}