PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis Article Swipe
Zicheng Wang
,
Zhenghao Chen
,
Yiming Wu
,
Zhen Zhao
,
Luping Zhou
,
Dong Xu
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2405.15463
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2405.15463
Point cloud analysis has seen substantial advancements due to deep learning, although previous Transformer-based methods excel at modeling long-range dependencies on this task, their computational demands are substantial. Conversely, the Mamba offers greater efficiency but shows limited potential compared with Transformer-based methods. In this study, we introduce PoinTramba, a pioneering hybrid framework that synergies the analytical power of Transformer with the remarkable computational efficiency of Mamba for enhanced point cloud analysis. Specifically, our approach first segments point clouds into groups, where the Transformer meticulously captures intricate intra-group dependencies and produces group embeddings, whose inter-group relationships will be simultaneously and adeptly captured by efficient Mamba architecture, ensuring comprehensive analysis. Unlike previous Mamba approaches, we introduce a bi-directional importance-aware ordering (BIO) strategy to tackle the challenges of random ordering effects. This innovative strategy intelligently reorders group embeddings based on their calculated importance scores, significantly enhancing Mamba's performance and optimizing the overall analytical process. Our framework achieves a superior balance between computational efficiency and analytical performance by seamlessly integrating these advanced techniques, marking a substantial leap forward in point cloud analysis. Extensive experiments on datasets such as ScanObjectNN, ModelNet40, and ShapeNetPart demonstrate the effectiveness of our approach, establishing a new state-of-the-art analysis benchmark on point cloud recognition. For the first time, this paradigm leverages the combined strengths of both Transformer and Mamba architectures, facilitating a new standard in the field. The code is available at https://github.com/xiaoyao3302/PoinTramba.
Related Topics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2405.15463
- https://arxiv.org/pdf/2405.15463
- OA Status
- green
- Cited By
- 7
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4399062386
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4399062386Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2405.15463Digital Object Identifier
- Title
-
PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud AnalysisWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-05-24Full publication date if available
- Authors
-
Zicheng Wang, Zhenghao Chen, Yiming Wu, Zhen Zhao, Luping Zhou, Dong XuList of authors in order
- Landing page
-
https://arxiv.org/abs/2405.15463Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2405.15463Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2405.15463Direct OA link when available
- Concepts
-
Transformer, Computer science, Engineering, Electrical engineering, VoltageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
7Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 7Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4399062386 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2405.15463 |
| ids.doi | https://doi.org/10.48550/arxiv.2405.15463 |
| ids.openalex | https://openalex.org/W4399062386 |
| fwci | |
| type | preprint |
| title | PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11211 |
| topics[0].field.id | https://openalex.org/fields/19 |
| topics[0].field.display_name | Earth and Planetary Sciences |
| topics[0].score | 0.9970999956130981 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1907 |
| topics[0].subfield.display_name | Geology |
| topics[0].display_name | 3D Surveying and Cultural Heritage |
| topics[1].id | https://openalex.org/T10638 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9961000084877014 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Optical measurement and interference techniques |
| topics[2].id | https://openalex.org/T11164 |
| topics[2].field.id | https://openalex.org/fields/23 |
| topics[2].field.display_name | Environmental Science |
| topics[2].score | 0.9915000200271606 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2305 |
| topics[2].subfield.display_name | Environmental Engineering |
| topics[2].display_name | Remote Sensing and LiDAR Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C66322947 |
| concepts[0].level | 3 |
| concepts[0].score | 0.45197296142578125 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[0].display_name | Transformer |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.37091678380966187 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C127413603 |
| concepts[2].level | 0 |
| concepts[2].score | 0.18149572610855103 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[2].display_name | Engineering |
| concepts[3].id | https://openalex.org/C119599485 |
| concepts[3].level | 1 |
| concepts[3].score | 0.137131929397583 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q43035 |
| concepts[3].display_name | Electrical engineering |
| concepts[4].id | https://openalex.org/C165801399 |
| concepts[4].level | 2 |
| concepts[4].score | 0.0 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[4].display_name | Voltage |
| keywords[0].id | https://openalex.org/keywords/transformer |
| keywords[0].score | 0.45197296142578125 |
| keywords[0].display_name | Transformer |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.37091678380966187 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/engineering |
| keywords[2].score | 0.18149572610855103 |
| keywords[2].display_name | Engineering |
| keywords[3].id | https://openalex.org/keywords/electrical-engineering |
| keywords[3].score | 0.137131929397583 |
| keywords[3].display_name | Electrical engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2405.15463 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2405.15463 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2405.15463 |
| locations[1].id | doi:10.48550/arxiv.2405.15463 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2405.15463 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100347959 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-8351-0329 |
| authorships[0].author.display_name | Zicheng Wang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wang, Zicheng |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5064120901 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-0155-4462 |
| authorships[1].author.display_name | Zhenghao Chen |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Chen, Zhenghao |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100539790 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-7892-9088 |
| authorships[2].author.display_name | Yiming Wu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Wu, Yiming |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5072694516 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-0796-4078 |
| authorships[3].author.display_name | Zhen Zhao |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zhao, Zhen |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100643784 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-8762-2424 |
| authorships[4].author.display_name | Luping Zhou |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Zhou, Luping |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5102635854 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Dong Xu |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Xu, Dong |
| authorships[5].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2405.15463 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-05-28T00:00:00 |
| display_name | PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11211 |
| primary_topic.field.id | https://openalex.org/fields/19 |
| primary_topic.field.display_name | Earth and Planetary Sciences |
| primary_topic.score | 0.9970999956130981 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1907 |
| primary_topic.subfield.display_name | Geology |
| primary_topic.display_name | 3D Surveying and Cultural Heritage |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052, https://openalex.org/W2382290278, https://openalex.org/W4395014643 |
| cited_by_count | 7 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 7 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2405.15463 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2405.15463 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2405.15463 |
| primary_location.id | pmh:oai:arXiv.org:2405.15463 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2405.15463 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2405.15463 |
| publication_date | 2024-05-24 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 48, 114, 154, 170, 195, 221 |
| abstract_inverted_index.In | 42 |
| abstract_inverted_index.as | 183 |
| abstract_inverted_index.at | 16, 231 |
| abstract_inverted_index.be | 96 |
| abstract_inverted_index.by | 101, 163 |
| abstract_inverted_index.in | 174, 224 |
| abstract_inverted_index.is | 229 |
| abstract_inverted_index.of | 57, 64, 124, 191, 214 |
| abstract_inverted_index.on | 20, 136, 180, 200 |
| abstract_inverted_index.to | 8, 120 |
| abstract_inverted_index.we | 45, 112 |
| abstract_inverted_index.For | 204 |
| abstract_inverted_index.Our | 151 |
| abstract_inverted_index.The | 227 |
| abstract_inverted_index.and | 88, 98, 145, 160, 186, 217 |
| abstract_inverted_index.are | 26 |
| abstract_inverted_index.but | 34 |
| abstract_inverted_index.due | 7 |
| abstract_inverted_index.for | 66 |
| abstract_inverted_index.has | 3 |
| abstract_inverted_index.new | 196, 222 |
| abstract_inverted_index.our | 72, 192 |
| abstract_inverted_index.the | 29, 54, 60, 81, 122, 147, 189, 205, 211, 225 |
| abstract_inverted_index.This | 128 |
| abstract_inverted_index.both | 215 |
| abstract_inverted_index.code | 228 |
| abstract_inverted_index.deep | 9 |
| abstract_inverted_index.into | 78 |
| abstract_inverted_index.leap | 172 |
| abstract_inverted_index.seen | 4 |
| abstract_inverted_index.such | 182 |
| abstract_inverted_index.that | 52 |
| abstract_inverted_index.this | 21, 43, 208 |
| abstract_inverted_index.will | 95 |
| abstract_inverted_index.with | 39, 59 |
| abstract_inverted_index.(BIO) | 118 |
| abstract_inverted_index.Mamba | 30, 65, 103, 110, 218 |
| abstract_inverted_index.Point | 0 |
| abstract_inverted_index.based | 135 |
| abstract_inverted_index.cloud | 1, 69, 176, 202 |
| abstract_inverted_index.excel | 15 |
| abstract_inverted_index.first | 74, 206 |
| abstract_inverted_index.group | 90, 133 |
| abstract_inverted_index.point | 68, 76, 175, 201 |
| abstract_inverted_index.power | 56 |
| abstract_inverted_index.shows | 35 |
| abstract_inverted_index.task, | 22 |
| abstract_inverted_index.their | 23, 137 |
| abstract_inverted_index.these | 166 |
| abstract_inverted_index.time, | 207 |
| abstract_inverted_index.where | 80 |
| abstract_inverted_index.whose | 92 |
| abstract_inverted_index.Unlike | 108 |
| abstract_inverted_index.clouds | 77 |
| abstract_inverted_index.field. | 226 |
| abstract_inverted_index.hybrid | 50 |
| abstract_inverted_index.offers | 31 |
| abstract_inverted_index.random | 125 |
| abstract_inverted_index.study, | 44 |
| abstract_inverted_index.tackle | 121 |
| abstract_inverted_index.Mamba's | 143 |
| abstract_inverted_index.adeptly | 99 |
| abstract_inverted_index.balance | 156 |
| abstract_inverted_index.between | 157 |
| abstract_inverted_index.demands | 25 |
| abstract_inverted_index.forward | 173 |
| abstract_inverted_index.greater | 32 |
| abstract_inverted_index.groups, | 79 |
| abstract_inverted_index.limited | 36 |
| abstract_inverted_index.marking | 169 |
| abstract_inverted_index.methods | 14 |
| abstract_inverted_index.overall | 148 |
| abstract_inverted_index.scores, | 140 |
| abstract_inverted_index.achieves | 153 |
| abstract_inverted_index.advanced | 167 |
| abstract_inverted_index.although | 11 |
| abstract_inverted_index.analysis | 2, 198 |
| abstract_inverted_index.approach | 73 |
| abstract_inverted_index.captured | 100 |
| abstract_inverted_index.captures | 84 |
| abstract_inverted_index.combined | 212 |
| abstract_inverted_index.compared | 38 |
| abstract_inverted_index.datasets | 181 |
| abstract_inverted_index.effects. | 127 |
| abstract_inverted_index.enhanced | 67 |
| abstract_inverted_index.ensuring | 105 |
| abstract_inverted_index.methods. | 41 |
| abstract_inverted_index.modeling | 17 |
| abstract_inverted_index.ordering | 117, 126 |
| abstract_inverted_index.paradigm | 209 |
| abstract_inverted_index.previous | 12, 109 |
| abstract_inverted_index.process. | 150 |
| abstract_inverted_index.produces | 89 |
| abstract_inverted_index.reorders | 132 |
| abstract_inverted_index.segments | 75 |
| abstract_inverted_index.standard | 223 |
| abstract_inverted_index.strategy | 119, 130 |
| abstract_inverted_index.superior | 155 |
| abstract_inverted_index.Extensive | 178 |
| abstract_inverted_index.analysis. | 70, 107, 177 |
| abstract_inverted_index.approach, | 193 |
| abstract_inverted_index.available | 230 |
| abstract_inverted_index.benchmark | 199 |
| abstract_inverted_index.efficient | 102 |
| abstract_inverted_index.enhancing | 142 |
| abstract_inverted_index.framework | 51, 152 |
| abstract_inverted_index.intricate | 85 |
| abstract_inverted_index.introduce | 46, 113 |
| abstract_inverted_index.learning, | 10 |
| abstract_inverted_index.leverages | 210 |
| abstract_inverted_index.potential | 37 |
| abstract_inverted_index.strengths | 213 |
| abstract_inverted_index.synergies | 53 |
| abstract_inverted_index.analytical | 55, 149, 161 |
| abstract_inverted_index.calculated | 138 |
| abstract_inverted_index.challenges | 123 |
| abstract_inverted_index.efficiency | 33, 63, 159 |
| abstract_inverted_index.embeddings | 134 |
| abstract_inverted_index.importance | 139 |
| abstract_inverted_index.innovative | 129 |
| abstract_inverted_index.long-range | 18 |
| abstract_inverted_index.optimizing | 146 |
| abstract_inverted_index.pioneering | 49 |
| abstract_inverted_index.remarkable | 61 |
| abstract_inverted_index.seamlessly | 164 |
| abstract_inverted_index.Conversely, | 28 |
| abstract_inverted_index.ModelNet40, | 185 |
| abstract_inverted_index.PoinTramba, | 47 |
| abstract_inverted_index.Transformer | 58, 82, 216 |
| abstract_inverted_index.approaches, | 111 |
| abstract_inverted_index.demonstrate | 188 |
| abstract_inverted_index.embeddings, | 91 |
| abstract_inverted_index.experiments | 179 |
| abstract_inverted_index.integrating | 165 |
| abstract_inverted_index.inter-group | 93 |
| abstract_inverted_index.intra-group | 86 |
| abstract_inverted_index.performance | 144, 162 |
| abstract_inverted_index.substantial | 5, 171 |
| abstract_inverted_index.techniques, | 168 |
| abstract_inverted_index.ShapeNetPart | 187 |
| abstract_inverted_index.advancements | 6 |
| abstract_inverted_index.dependencies | 19, 87 |
| abstract_inverted_index.establishing | 194 |
| abstract_inverted_index.facilitating | 220 |
| abstract_inverted_index.meticulously | 83 |
| abstract_inverted_index.recognition. | 203 |
| abstract_inverted_index.substantial. | 27 |
| abstract_inverted_index.ScanObjectNN, | 184 |
| abstract_inverted_index.Specifically, | 71 |
| abstract_inverted_index.architecture, | 104 |
| abstract_inverted_index.comprehensive | 106 |
| abstract_inverted_index.computational | 24, 62, 158 |
| abstract_inverted_index.effectiveness | 190 |
| abstract_inverted_index.intelligently | 131 |
| abstract_inverted_index.relationships | 94 |
| abstract_inverted_index.significantly | 141 |
| abstract_inverted_index.architectures, | 219 |
| abstract_inverted_index.bi-directional | 115 |
| abstract_inverted_index.simultaneously | 97 |
| abstract_inverted_index.importance-aware | 116 |
| abstract_inverted_index.state-of-the-art | 197 |
| abstract_inverted_index.Transformer-based | 13, 40 |
| abstract_inverted_index.https://github.com/xiaoyao3302/PoinTramba. | 232 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |