{"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/point-bert-pre-training-3d-point-cloud","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","arxiv_id":"2111.14819","date":"2021-11-29","proceeding":"CVPR 2022 1","authors":["Xumin Yu","Lulu Tang","Yongming Rao","Tiejun Huang","Jie zhou","Jiwen Lu"],"abstract":"We present Point-BERT, a new paradigm for learning Transformers to generalize the concept of BERT to 3D point cloud. Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers. Specifically, we first divide a point cloud into several local point patches, and a point cloud Tokenizer with a discrete Variational AutoEncoder (dVAE) is designed to generate discrete point tokens containing meaningful local information. Then, we randomly mask out some patches of input point clouds and feed them into the backbone Transformers. The pre-training objective is to recover the original point tokens at the masked locations under the supervision of point tokens obtained by the Tokenizer. Extensive experiments demonstrate that the proposed BERT-style pre-training strategy significantly improves the performance of standard point cloud Transformers. Equipped with our pre-training strategy, we show that a pure Transformer architecture attains 93.8% accuracy on ModelNet40 and 83.1% accuracy on the hardest setting of ScanObjectNN, surpassing carefully designed point cloud models with much fewer hand-made designs. We also demonstrate that the representations learned by Point-BERT transfer well to new tasks and domains, where our models largely advance the state-of-the-art of few-shot point cloud classification task. The code and pre-trained models are available at https://github.com/lulutang0608/Point-BERT","url_abs":"https://arxiv.org/abs/2111.14819v2","url_pdf":"https://arxiv.org/pdf/2111.14819v2.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":"point-bert-pre-training-3d-point-cloud","repo_url":"https://github.com/lulutang0608/Point-BERT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"point-bert-pre-training-3d-point-cloud","repo_url":"https://github.com/julie-tang00/point-bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"point-bert-pre-training-3d-point-cloud","repo_url":"https://github.com/lmd0311/pointmamba","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"3d-point-cloud-linear-classification","task_name":"3D Point Cloud Linear Classification"},{"task_slug":"few-shot-3d-point-cloud-classification","task_name":"Few-Shot 3D Point Cloud Classification"},{"task_slug":"few-shot-point-cloud-classification","task_name":"Few-Shot Point Cloud Classification"},{"task_slug":"point-cloud-classification","task_name":"Point Cloud Classification"},{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"Point-BERT","rank_in_archive_order":44,"of":111,"metrics":{"Overall Accuracy":"93.8"},"uses_additional_data":true},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"Point-BERT","rank_in_archive_order":64,"of":77,"metrics":{"OBJ-BG (OA)":"87.43","OBJ-ONLY (OA)":"88.12","Overall Accuracy":"83.1"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-3","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 10-way (10-shot)","model":"Point-BERT","rank_in_archive_order":18,"of":31,"metrics":{"Overall Accuracy":"91.0","Standard Deviation":"5.4"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-4","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 10-way (20-shot)","model":"Point-BERT","rank_in_archive_order":18,"of":31,"metrics":{"Overall Accuracy":"92.7","Standard Deviation":"5.1"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-1","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 5-way (10-shot)","model":"Point-BERT","rank_in_archive_order":17,"of":30,"metrics":{"Overall Accuracy":"94.6","Standard Deviation":"3.1"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-2","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 5-way (20-shot)","model":"Point-BERT","rank_in_archive_order":18,"of":30,"metrics":{"Overall Accuracy":"96.3","Standard Deviation":"2.7"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.14819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14819"}},"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/lmd0311/pointmamba","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lulutang0608/Point-BERT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/julie-tang00/point-bert","reach":null}],"summary":{"ran_fixture":3,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"repositories":1},"listed":{"samples":1,"ran":1,"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":"0771dfb62d38a68e","entry":"evaluate_svm","repo":"julie-tang00/point-bert","repo_kind":"listed","path":"tools/runner_BERT_pretrain.py","file_url":"https://github.com/julie-tang00/point-bert/blob/HEAD/tools/runner_BERT_pretrain.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0771dfb62d38a68e"}},{"code_sha256_prefix":"3fc6f6b239b211f9","entry":"knn_point","repo":"lulutang0608/Point-BERT","repo_kind":"official","path":"models/dvae.py","file_url":"https://github.com/lulutang0608/Point-BERT/blob/HEAD/models/dvae.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3fc6f6b239b211f9"}},{"code_sha256_prefix":"4783fbece52f500e","entry":"pc_normalize","repo":"lulutang0608/Point-BERT","repo_kind":"official","path":"datasets/ModelNetDataset.py","file_url":"https://github.com/lulutang0608/Point-BERT/blob/HEAD/datasets/ModelNetDataset.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4783fbece52f500e"}},{"code_sha256_prefix":"3bfe172e686075cd","entry":"square_distance","repo":"lulutang0608/Point-BERT","repo_kind":"official","path":"models/dvae.py","file_url":"https://github.com/lulutang0608/Point-BERT/blob/HEAD/models/dvae.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3bfe172e686075cd"}},{"code_sha256_prefix":"73cecca9f3575f09","entry":"concat_all_gather","repo":"lulutang0608/Point-BERT","repo_kind":"official","path":"models/Point_BERT.py","file_url":"https://github.com/lulutang0608/Point-BERT/blob/HEAD/models/Point_BERT.py","link_basis":"plan_row","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":"73cecca9f3575f09"}},{"code_sha256_prefix":"f80066a00e7156a2","entry":"farthest_point_sample","repo":"lulutang0608/Point-BERT","repo_kind":"official","path":"datasets/ModelNetDataset.py","file_url":"https://github.com/lulutang0608/Point-BERT/blob/HEAD/datasets/ModelNetDataset.py","link_basis":"harvester_set","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":"f80066a00e7156a2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}