{"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/self-supervised-point-cloud-completion-via","title":"Self-Supervised Point Cloud Completion via Inpainting","arxiv_id":"2111.10701","date":"2021-11-21","proceeding":null,"authors":["Himangi Mittal","Brian Okorn","Arpit Jangid","David Held"],"abstract":"When navigating in urban environments, many of the objects that need to be tracked and avoided are heavily occluded. Planning and tracking using these partial scans can be challenging. The aim of this work is to learn to complete these partial point clouds, giving us a full understanding of the object's geometry using only partial observations. Previous methods achieve this with the help of complete, ground-truth annotations of the target objects, which are available only for simulated datasets. However, such ground truth is unavailable for real-world LiDAR data. In this work, we present a self-supervised point cloud completion algorithm, PointPnCNet, which is trained only on partial scans without assuming access to complete, ground-truth annotations. Our method achieves this via inpainting. We remove a portion of the input data and train the network to complete the missing region. As it is difficult to determine which regions were occluded in the initial cloud and which were synthetically removed, our network learns to complete the full cloud, including the missing regions in the initial partial cloud. We show that our method outperforms previous unsupervised and weakly-supervised methods on both the synthetic dataset, ShapeNet, and real-world LiDAR dataset, Semantic KITTI.","url_abs":"https://arxiv.org/abs/2111.10701v1","url_pdf":"https://arxiv.org/pdf/2111.10701v1.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":"self-supervised-point-cloud-completion-via","repo_url":"https://github.com/HimangiM/Self-Supervised-Point-Cloud-Completion-via-Inpainting","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"point-cloud-completion","task_name":"Point Cloud Completion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.10701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.10701"}},"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/HimangiM/Self-Supervised-Point-Cloud-Completion-via-Inpainting","reach":null}],"summary":{"ran_fixture":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"0f9306d74063252b","entry":"pc_sensor_to_canonical","repo":"HimangiM/Self-Supervised-Point-Cloud-Completion-via-Inpainting","repo_kind":"official","path":"train_shapenet.py","file_url":"https://github.com/HimangiM/Self-Supervised-Point-Cloud-Completion-via-Inpainting/blob/HEAD/train_shapenet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0f9306d74063252b"}},{"code_sha256_prefix":"c8b9d21880bdce4e","entry":"resample_pcd","repo":"HimangiM/Self-Supervised-Point-Cloud-Completion-via-Inpainting","repo_kind":"official","path":"train_semantickitti.py","file_url":"https://github.com/HimangiM/Self-Supervised-Point-Cloud-Completion-via-Inpainting/blob/HEAD/train_semantickitti.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c8b9d21880bdce4e"}},{"code_sha256_prefix":"65494796fd65b0b7","entry":"return_octants","repo":"HimangiM/Self-Supervised-Point-Cloud-Completion-via-Inpainting","repo_kind":"official","path":"train_shapenet.py","file_url":"https://github.com/HimangiM/Self-Supervised-Point-Cloud-Completion-via-Inpainting/blob/HEAD/train_shapenet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"65494796fd65b0b7"}},{"code_sha256_prefix":"035bb73ccdf94198","entry":"return_octants","repo":"HimangiM/Self-Supervised-Point-Cloud-Completion-via-Inpainting","repo_kind":"official","path":"train_semantickitti.py","file_url":"https://github.com/HimangiM/Self-Supervised-Point-Cloud-Completion-via-Inpainting/blob/HEAD/train_semantickitti.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"035bb73ccdf94198"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}