{"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/generalized-few-shot-3d-point-cloud","title":"Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model","arxiv_id":"2503.16282","date":"2025-03-20","proceeding":"CVPR 2025 1","authors":["Zhaochong An","Guolei Sun","Yun Liu","Runjia Li","Junlin Han","Ender Konukoglu","Serge Belongie"],"abstract":"Generalized few-shot 3D point cloud segmentation (GFS-PCS) adapts models to new classes with few support samples while retaining base class segmentation. Existing GFS-PCS methods enhance prototypes via interacting with support or query features but remain limited by sparse knowledge from few-shot samples. Meanwhile, 3D vision-language models (3D VLMs), generalizing across open-world novel classes, contain rich but noisy novel class knowledge. In this work, we introduce a GFS-PCS framework that synergizes dense but noisy pseudo-labels from 3D VLMs with precise yet sparse few-shot samples to maximize the strengths of both, named GFS-VL. Specifically, we present a prototype-guided pseudo-label selection to filter low-quality regions, followed by an adaptive infilling strategy that combines knowledge from pseudo-label contexts and few-shot samples to adaptively label the filtered, unlabeled areas. Additionally, we design a novel-base mix strategy to embed few-shot samples into training scenes, preserving essential context for improved novel class learning. Moreover, recognizing the limited diversity in current GFS-PCS benchmarks, we introduce two challenging benchmarks with diverse novel classes for comprehensive generalization evaluation. Experiments validate the effectiveness of our framework across models and datasets. Our approach and benchmarks provide a solid foundation for advancing GFS-PCS in the real world. The code is at https://github.com/ZhaochongAn/GFS-VL","url_abs":"https://arxiv.org/abs/2503.16282v2","url_pdf":"https://arxiv.org/pdf/2503.16282v2.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":"generalized-few-shot-3d-point-cloud","repo_url":"https://github.com/zhaochongan/gfs-vl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generalized-few-shot-3d-point-cloud","repo_url":"https://github.com/zhaochongan/coseg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.16282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16282"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/zhaochongan/gfs-vl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhaochongan/coseg","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":3,"samples":[{"code_sha256_prefix":"508f4d352d45fee7","entry":"generate_pseudo_label_batch","repo":"zhaochongan/gfs-vl","repo_kind":"official","path":"pointcept/models/PLA/pcseg/utils/pseudo_label_utils.py","file_url":"https://github.com/zhaochongan/gfs-vl/blob/HEAD/pointcept/models/PLA/pcseg/utils/pseudo_label_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"508f4d352d45fee7"}},{"code_sha256_prefix":"1e886c6dd9061323","entry":"generate_pseudo_labels","repo":"zhaochongan/gfs-vl","repo_kind":"official","path":"pointcept/models/PLA/pcseg/utils/pseudo_label_utils.py","file_url":"https://github.com/zhaochongan/gfs-vl/blob/HEAD/pointcept/models/PLA/pcseg/utils/pseudo_label_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1e886c6dd9061323"}},{"code_sha256_prefix":"60c7ad59a6a80229","entry":"load_data_to_gpu","repo":"zhaochongan/gfs-vl","repo_kind":"official","path":"pointcept/models/PLA/pcseg/utils/pseudo_label_utils.py","file_url":"https://github.com/zhaochongan/gfs-vl/blob/HEAD/pointcept/models/PLA/pcseg/utils/pseudo_label_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"60c7ad59a6a80229"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}