{"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/mamba3d-enhancing-local-features-for-3d-point","title":"Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model","arxiv_id":"2404.14966","date":"2024-04-23","proceeding":null,"authors":["Xu Han","Yuan Tang","Zhaoxuan Wang","Xianzhi Li"],"abstract":"Existing Transformer-based models for point cloud analysis suffer from quadratic complexity, leading to compromised point cloud resolution and information loss. In contrast, the newly proposed Mamba model, based on state space models (SSM), outperforms Transformer in multiple areas with only linear complexity. However, the straightforward adoption of Mamba does not achieve satisfactory performance on point cloud tasks. In this work, we present Mamba3D, a state space model tailored for point cloud learning to enhance local feature extraction, achieving superior performance, high efficiency, and scalability potential. Specifically, we propose a simple yet effective Local Norm Pooling (LNP) block to extract local geometric features. Additionally, to obtain better global features, we introduce a bidirectional SSM (bi-SSM) with both a token forward SSM and a novel backward SSM that operates on the feature channel. Extensive experimental results show that Mamba3D surpasses Transformer-based counterparts and concurrent works in multiple tasks, with or without pre-training. Notably, Mamba3D achieves multiple SoTA, including an overall accuracy of 92.6% (train from scratch) on the ScanObjectNN and 95.1% (with single-modal pre-training) on the ModelNet40 classification task, with only linear complexity. Our code and weights are available at https://github.com/xhanxu/Mamba3D.","url_abs":"https://arxiv.org/abs/2404.14966v2","url_pdf":"https://arxiv.org/pdf/2404.14966v2.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":"mamba3d-enhancing-local-features-for-3d-point","repo_url":"https://github.com/xhanxu/Mamba3D","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"state-space-models","task_name":"State Space Models"},{"task_slug":"supervised-only-3d-point-cloud-classification","task_name":"Supervised Only 3D Point Cloud Classification"}],"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":"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":"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"Mamba3D + Point-MAE","rank_in_archive_order":2,"of":111,"metrics":{"FLOPs":"3.9G","Number of params":"16.9M","Overall Accuracy":"95.1"},"uses_additional_data":true},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"Mamba3D","rank_in_archive_order":9,"of":77,"metrics":{"FLOPs":"3.9G","Number of params":"16.9M","OBJ-BG (OA)":"94.49","OBJ-ONLY (OA)":"92.43","Overall Accuracy":"92.64"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"Mamba3D (no voting)","rank_in_archive_order":10,"of":77,"metrics":{"FLOPs":"3.9G","Number of params":"16.9M","OBJ-BG (OA)":"92.94","OBJ-ONLY (OA)":"92.08","Overall Accuracy":"91.81"},"uses_additional_data":false},{"leaderboard":"/sota/supervised-only-3d-point-cloud-classification","task":"Supervised Only 3D Point Cloud Classification","dataset":"ScanObjectNN","model":"Mamba3D","rank_in_archive_order":1,"of":12,"metrics":{"GFLOPs":"3.9","Number of params (M)":"16.9","Overall Accuracy (PB_T50_RS)":"92.64"},"uses_additional_data":false},{"leaderboard":"/sota/supervised-only-3d-point-cloud-classification","task":"Supervised Only 3D Point Cloud Classification","dataset":"ScanObjectNN","model":"Mamba3D (no voting)","rank_in_archive_order":2,"of":12,"metrics":{"GFLOPs":"3.9","Number of params (M)":"16.9","Overall Accuracy (PB_T50_RS)":"91.81"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.14966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14966"}},"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/xhanxu/Mamba3D","reach":{"status":"ok"}}],"summary":{"ran_honours":2,"ran":3,"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":7,"samples":[{"code_sha256_prefix":"f50a8d20efb35c68","entry":"broadcat","repo":"xhanxu/Mamba3D","repo_kind":"official","path":"models/rope.py","file_url":"https://github.com/xhanxu/Mamba3D/blob/HEAD/models/rope.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f50a8d20efb35c68"}},{"code_sha256_prefix":"8211b3ca522ad7c8","entry":"get_z_order","repo":"xhanxu/Mamba3D","repo_kind":"official","path":"models/z_order.py","file_url":"https://github.com/xhanxu/Mamba3D/blob/HEAD/models/z_order.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8211b3ca522ad7c8"}},{"code_sha256_prefix":"4783fbece52f500e","entry":"pc_normalize","repo":"xhanxu/Mamba3D","repo_kind":"official","path":"datasets/ModelNetDataset.py","file_url":"https://github.com/xhanxu/Mamba3D/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4783fbece52f500e"}},{"code_sha256_prefix":"58823d9435a8751b","entry":"rotate_half","repo":"xhanxu/Mamba3D","repo_kind":"official","path":"models/rope.py","file_url":"https://github.com/xhanxu/Mamba3D/blob/HEAD/models/rope.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"58823d9435a8751b"}},{"code_sha256_prefix":"936ad378b238e868","entry":"round_to_int_32","repo":"xhanxu/Mamba3D","repo_kind":"official","path":"models/z_order.py","file_url":"https://github.com/xhanxu/Mamba3D/blob/HEAD/models/z_order.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"936ad378b238e868"}},{"code_sha256_prefix":"2901d555b5635d05","entry":"split_by_3","repo":"xhanxu/Mamba3D","repo_kind":"official","path":"models/z_order.py","file_url":"https://github.com/xhanxu/Mamba3D/blob/HEAD/models/z_order.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2901d555b5635d05"}},{"code_sha256_prefix":"f80066a00e7156a2","entry":"farthest_point_sample","repo":"xhanxu/Mamba3D","repo_kind":"official","path":"datasets/ModelNetDataset.py","file_url":"https://github.com/xhanxu/Mamba3D/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f80066a00e7156a2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}