{"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/bipointnet-binary-neural-network-for-point-2","title":"BiPointNet: Binary Neural Network for Point Clouds","arxiv_id":"2010.05501","date":"2020-10-12","proceeding":"ICLR 2021 1","authors":["Haotong Qin","Zhongang Cai","Mingyuan Zhang","Yifu Ding","Haiyu Zhao","Shuai Yi","Xianglong Liu","Hao Su"],"abstract":"To alleviate the resource constraint for real-time point cloud applications that run on edge devices, in this paper we present BiPointNet, the first model binarization approach for efficient deep learning on point clouds. We discover that the immense performance drop of binarized models for point clouds mainly stems from two challenges: aggregation-induced feature homogenization that leads to a degradation of information entropy, and scale distortion that hinders optimization and invalidates scale-sensitive structures. With theoretical justifications and in-depth analysis, our BiPointNet introduces Entropy-Maximizing Aggregation (EMA) to modulate the distribution before aggregation for the maximum information entropy, and Layer-wise Scale Recovery (LSR) to efficiently restore feature representation capacity. Extensive experiments show that BiPointNet outperforms existing binarization methods by convincing margins, at the level even comparable with the full precision counterpart. We highlight that our techniques are generic, guaranteeing significant improvements on various fundamental tasks and mainstream backbones. Moreover, BiPointNet gives an impressive 14.7x speedup and 18.9x storage saving on real-world resource-constrained devices.","url_abs":"https://arxiv.org/abs/2010.05501v4","url_pdf":"https://arxiv.org/pdf/2010.05501v4.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":"bipointnet-binary-neural-network-for-point-2","repo_url":"https://github.com/htqin/BiPointNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"binarization","task_name":"Binarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.05501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05501"}},"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/htqin/BiPointNet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"c86eea5b6a6e351f","entry":"BiMLP","repo":"htqin/BiPointNet","repo_kind":"official","path":"models/basic.py","file_url":"https://github.com/htqin/BiPointNet/blob/HEAD/models/basic.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c86eea5b6a6e351f"}},{"code_sha256_prefix":"6838d7b0de55f774","entry":"BwMLP","repo":"htqin/BiPointNet","repo_kind":"official","path":"models/basic.py","file_url":"https://github.com/htqin/BiPointNet/blob/HEAD/models/basic.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6838d7b0de55f774"}},{"code_sha256_prefix":"e549cf99abccf5c0","entry":"MLP","repo":"htqin/BiPointNet","repo_kind":"official","path":"models/basic.py","file_url":"https://github.com/htqin/BiPointNet/blob/HEAD/models/basic.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e549cf99abccf5c0"}},{"code_sha256_prefix":"ee84bdaf4bb72c2a","entry":"cat_data_list","repo":"htqin/BiPointNet","repo_kind":"official","path":"datasets/s3dis.py","file_url":"https://github.com/htqin/BiPointNet/blob/HEAD/datasets/s3dis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee84bdaf4bb72c2a"}},{"code_sha256_prefix":"cc3d1b6d0a545eb0","entry":"create_logger","repo":"htqin/BiPointNet","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/htqin/BiPointNet/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc3d1b6d0a545eb0"}},{"code_sha256_prefix":"380c68b7dce6f8fa","entry":"parse_cfg","repo":"htqin/BiPointNet","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/htqin/BiPointNet/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"380c68b7dce6f8fa"}},{"code_sha256_prefix":"46ab0a5b3a6f6dd9","entry":"pc_normalize","repo":"htqin/BiPointNet","repo_kind":"official","path":"datasets/modelnet2.py","file_url":"https://github.com/htqin/BiPointNet/blob/HEAD/datasets/modelnet2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46ab0a5b3a6f6dd9"}},{"code_sha256_prefix":"05d15e1d5a61b4fc","entry":"resume_last","repo":"htqin/BiPointNet","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/htqin/BiPointNet/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05d15e1d5a61b4fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}