{"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/pointgpt-auto-regressively-generative-pre-1","title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","arxiv_id":"2305.11487","date":"2023-05-19","proceeding":"NeurIPS 2023 11","authors":["Guangyan Chen","Meiling Wang","Yi Yang","Kai Yu","Li Yuan","Yufeng Yue"],"abstract":"Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel approach that extends the concept of GPT to point clouds, addressing the challenges associated with disorder properties, low information density, and task gaps. Specifically, a point cloud auto-regressive generation task is proposed to pre-train transformer models. Our method partitions the input point cloud into multiple point patches and arranges them in an ordered sequence based on their spatial proximity. Then, an extractor-generator based transformer decoder, with a dual masking strategy, learns latent representations conditioned on the preceding point patches, aiming to predict the next one in an auto-regressive manner. Our scalable approach allows for learning high-capacity models that generalize well, achieving state-of-the-art performance on various downstream tasks. In particular, our approach achieves classification accuracies of 94.9% on the ModelNet40 dataset and 93.4% on the ScanObjectNN dataset, outperforming all other transformer models. Furthermore, our method also attains new state-of-the-art accuracies on all four few-shot learning benchmarks.","url_abs":"https://arxiv.org/abs/2305.11487v2","url_pdf":"https://arxiv.org/pdf/2305.11487v2.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":"pointgpt-auto-regressively-generative-pre-1","repo_url":"https://github.com/CGuangyan-BIT/PointGPT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"few-shot-3d-point-cloud-classification","task_name":"Few-Shot 3D Point Cloud Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt","method_name":"GPT"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"PointGPT","rank_in_archive_order":7,"of":77,"metrics":{"OBJ-BG (OA)":"97.2","OBJ-ONLY (OA)":"96.6","Overall Accuracy":"93.4"},"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":"PointGPT","rank_in_archive_order":3,"of":31,"metrics":{"Overall Accuracy":"94.3","Standard Deviation":"3.3"},"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":"PointGPT","rank_in_archive_order":4,"of":31,"metrics":{"Overall Accuracy":"96.1","Standard Deviation":"2.8"},"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":"PointGPT","rank_in_archive_order":1,"of":30,"metrics":{"Overall Accuracy":"98.0","Standard Deviation":"1.9"},"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":"PointGPT","rank_in_archive_order":4,"of":30,"metrics":{"Overall Accuracy":"99.0","Standard Deviation":"1.0"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.11487","atlas_url":"https://app.syntology.ai/?focus=2305.11487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11487"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/CGuangyan-BIT/PointGPT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_honours":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"f80066a00e7156a2","entry":"farthest_point_sample","repo":"CGuangyan-BIT/PointGPT","repo_kind":"official","path":"datasets/ModelNetDataset.py","file_url":"https://github.com/CGuangyan-BIT/PointGPT/blob/HEAD/datasets/ModelNetDataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f80066a00e7156a2"}},{"code_sha256_prefix":"8211b3ca522ad7c8","entry":"get_z_order","repo":"CGuangyan-BIT/PointGPT","repo_kind":"official","path":"models/z_order.py","file_url":"https://github.com/CGuangyan-BIT/PointGPT/blob/HEAD/models/z_order.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8211b3ca522ad7c8"}},{"code_sha256_prefix":"4783fbece52f500e","entry":"pc_normalize","repo":"CGuangyan-BIT/PointGPT","repo_kind":"official","path":"datasets/ModelNetDataset.py","file_url":"https://github.com/CGuangyan-BIT/PointGPT/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":"936ad378b238e868","entry":"round_to_int_32","repo":"CGuangyan-BIT/PointGPT","repo_kind":"official","path":"models/z_order.py","file_url":"https://github.com/CGuangyan-BIT/PointGPT/blob/HEAD/models/z_order.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"936ad378b238e868"}},{"code_sha256_prefix":"2901d555b5635d05","entry":"split_by_3","repo":"CGuangyan-BIT/PointGPT","repo_kind":"official","path":"models/z_order.py","file_url":"https://github.com/CGuangyan-BIT/PointGPT/blob/HEAD/models/z_order.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2901d555b5635d05"}},{"code_sha256_prefix":"74c3fe06cea2f553","entry":"square_distance","repo":"CGuangyan-BIT/PointGPT","repo_kind":"official","path":"segmentation/pointnet_util.py","file_url":"https://github.com/CGuangyan-BIT/PointGPT/blob/HEAD/segmentation/pointnet_util.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74c3fe06cea2f553"}},{"code_sha256_prefix":"b1227ddb721e2999","entry":"timeit","repo":"CGuangyan-BIT/PointGPT","repo_kind":"official","path":"segmentation/pointnet_util.py","file_url":"https://github.com/CGuangyan-BIT/PointGPT/blob/HEAD/segmentation/pointnet_util.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":"b1227ddb721e2999"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}