Online Language Splatting Article Swipe
Saimouli Katragadda
,
C.-W. Wu
,
Yue Leon Guo
,
X. T. Huang
,
Guoquan Huang
,
Ren Liu
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2503.09447
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2503.09447
To enable AI agents to interact seamlessly with both humans and 3D environments, they must not only perceive the 3D world accurately but also align human language with 3D spatial representations. While prior work has made significant progress by integrating language features into geometrically detailed 3D scene representations using 3D Gaussian Splatting (GS), these approaches rely on computationally intensive offline preprocessing of language features for each input image, limiting adaptability to new environments. In this work, we introduce Online Language Splatting, the first framework to achieve online, near real-time, open-vocabulary language mapping within a 3DGS-SLAM system without requiring pre-generated language features. The key challenge lies in efficiently fusing high-dimensional language features into 3D representations while balancing the computation speed, memory usage, rendering quality and open-vocabulary capability. To this end, we innovatively design: (1) a high-resolution CLIP embedding module capable of generating detailed language feature maps in 18ms per frame, (2) a two-stage online auto-encoder that compresses 768-dimensional CLIP features to 15 dimensions while preserving open-vocabulary capabilities, and (3) a color-language disentangled optimization approach to improve rendering quality. Experimental results show that our online method not only surpasses the state-of-the-art offline methods in accuracy but also achieves more than 40x efficiency boost, demonstrating the potential for dynamic and interactive AI applications.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2503.09447
- https://arxiv.org/pdf/2503.09447
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4415102947
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415102947Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2503.09447Digital Object Identifier
- Title
-
Online Language SplattingWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-03-12Full publication date if available
- Authors
-
Saimouli Katragadda, C.-W. Wu, Yue Leon Guo, X. T. Huang, Guoquan Huang, Ren LiuList of authors in order
- Landing page
-
https://arxiv.org/abs/2503.09447Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2503.09447Direct 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/2503.09447Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4415102947 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2503.09447 |
| ids.doi | https://doi.org/10.48550/arxiv.2503.09447 |
| ids.openalex | https://openalex.org/W4415102947 |
| fwci | |
| type | preprint |
| title | Online Language Splatting |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T13155 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.8510000109672546 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1709 |
| topics[0].subfield.display_name | Human-Computer Interaction |
| topics[0].display_name | Digital Communication and Language |
| topics[1].id | https://openalex.org/T12262 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.7716000080108643 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Hate Speech and Cyberbullying Detection |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2503.09447 |
| 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/2503.09447 |
| 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/2503.09447 |
| locations[1].id | doi:10.48550/arxiv.2503.09447 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2503.09447 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5086780394 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Saimouli Katragadda |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Katragadda, Saimouli |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5111406402 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | C.-W. Wu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wu, Cho-Ying |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100428834 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-8530-4809 |
| authorships[2].author.display_name | Yue Leon Guo |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Guo, Yuliang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5107903577 |
| authorships[3].author.orcid | https://orcid.org/0009-0000-0976-6764 |
| authorships[3].author.display_name | X. T. Huang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Huang, Xinyu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5008502528 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-9932-0685 |
| authorships[4].author.display_name | Guoquan Huang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Huang, Guoquan |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5078852225 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-4674-7292 |
| authorships[5].author.display_name | Ren Liu |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Ren, Liu |
| 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/2503.09447 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-13T00:00:00 |
| display_name | Online Language Splatting |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T13155 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.8510000109672546 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1709 |
| primary_topic.subfield.display_name | Human-Computer Interaction |
| primary_topic.display_name | Digital Communication and Language |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2503.09447 |
| 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/2503.09447 |
| 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/2503.09447 |
| primary_location.id | pmh:oai:arXiv.org:2503.09447 |
| 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/2503.09447 |
| 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/2503.09447 |
| publication_date | 2025-03-12 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 93, 133, 150, 168 |
| abstract_inverted_index.15 | 160 |
| abstract_inverted_index.3D | 11, 19, 28, 45, 49, 112 |
| abstract_inverted_index.AI | 2, 208 |
| abstract_inverted_index.In | 73 |
| abstract_inverted_index.To | 0, 126 |
| abstract_inverted_index.by | 38 |
| abstract_inverted_index.in | 105, 145, 191 |
| abstract_inverted_index.of | 61, 139 |
| abstract_inverted_index.on | 56 |
| abstract_inverted_index.to | 4, 70, 84, 159, 173 |
| abstract_inverted_index.we | 76, 129 |
| abstract_inverted_index.(1) | 132 |
| abstract_inverted_index.(2) | 149 |
| abstract_inverted_index.(3) | 167 |
| abstract_inverted_index.40x | 198 |
| abstract_inverted_index.The | 101 |
| abstract_inverted_index.and | 10, 123, 166, 206 |
| abstract_inverted_index.but | 22, 193 |
| abstract_inverted_index.for | 64, 204 |
| abstract_inverted_index.has | 34 |
| abstract_inverted_index.key | 102 |
| abstract_inverted_index.new | 71 |
| abstract_inverted_index.not | 15, 184 |
| abstract_inverted_index.our | 181 |
| abstract_inverted_index.per | 147 |
| abstract_inverted_index.the | 18, 81, 116, 187, 202 |
| abstract_inverted_index.18ms | 146 |
| abstract_inverted_index.CLIP | 135, 157 |
| abstract_inverted_index.also | 23, 194 |
| abstract_inverted_index.both | 8 |
| abstract_inverted_index.each | 65 |
| abstract_inverted_index.end, | 128 |
| abstract_inverted_index.into | 42, 111 |
| abstract_inverted_index.lies | 104 |
| abstract_inverted_index.made | 35 |
| abstract_inverted_index.maps | 144 |
| abstract_inverted_index.more | 196 |
| abstract_inverted_index.must | 14 |
| abstract_inverted_index.near | 87 |
| abstract_inverted_index.only | 16, 185 |
| abstract_inverted_index.rely | 55 |
| abstract_inverted_index.show | 179 |
| abstract_inverted_index.than | 197 |
| abstract_inverted_index.that | 154, 180 |
| abstract_inverted_index.they | 13 |
| abstract_inverted_index.this | 74, 127 |
| abstract_inverted_index.with | 7, 27 |
| abstract_inverted_index.work | 33 |
| abstract_inverted_index.(GS), | 52 |
| abstract_inverted_index.While | 31 |
| abstract_inverted_index.align | 24 |
| abstract_inverted_index.first | 82 |
| abstract_inverted_index.human | 25 |
| abstract_inverted_index.input | 66 |
| abstract_inverted_index.prior | 32 |
| abstract_inverted_index.scene | 46 |
| abstract_inverted_index.these | 53 |
| abstract_inverted_index.using | 48 |
| abstract_inverted_index.while | 114, 162 |
| abstract_inverted_index.work, | 75 |
| abstract_inverted_index.world | 20 |
| abstract_inverted_index.Online | 78 |
| abstract_inverted_index.agents | 3 |
| abstract_inverted_index.boost, | 200 |
| abstract_inverted_index.enable | 1 |
| abstract_inverted_index.frame, | 148 |
| abstract_inverted_index.fusing | 107 |
| abstract_inverted_index.humans | 9 |
| abstract_inverted_index.image, | 67 |
| abstract_inverted_index.memory | 119 |
| abstract_inverted_index.method | 183 |
| abstract_inverted_index.module | 137 |
| abstract_inverted_index.online | 152, 182 |
| abstract_inverted_index.speed, | 118 |
| abstract_inverted_index.system | 95 |
| abstract_inverted_index.usage, | 120 |
| abstract_inverted_index.within | 92 |
| abstract_inverted_index.achieve | 85 |
| abstract_inverted_index.capable | 138 |
| abstract_inverted_index.design: | 131 |
| abstract_inverted_index.dynamic | 205 |
| abstract_inverted_index.feature | 143 |
| abstract_inverted_index.improve | 174 |
| abstract_inverted_index.mapping | 91 |
| abstract_inverted_index.methods | 190 |
| abstract_inverted_index.offline | 59, 189 |
| abstract_inverted_index.online, | 86 |
| abstract_inverted_index.quality | 122 |
| abstract_inverted_index.results | 178 |
| abstract_inverted_index.spatial | 29 |
| abstract_inverted_index.without | 96 |
| abstract_inverted_index.Gaussian | 50 |
| abstract_inverted_index.Language | 79 |
| abstract_inverted_index.accuracy | 192 |
| abstract_inverted_index.achieves | 195 |
| abstract_inverted_index.approach | 172 |
| abstract_inverted_index.detailed | 44, 141 |
| abstract_inverted_index.features | 41, 63, 110, 158 |
| abstract_inverted_index.interact | 5 |
| abstract_inverted_index.language | 26, 40, 62, 90, 99, 109, 142 |
| abstract_inverted_index.limiting | 68 |
| abstract_inverted_index.perceive | 17 |
| abstract_inverted_index.progress | 37 |
| abstract_inverted_index.quality. | 176 |
| abstract_inverted_index.3DGS-SLAM | 94 |
| abstract_inverted_index.Splatting | 51 |
| abstract_inverted_index.balancing | 115 |
| abstract_inverted_index.challenge | 103 |
| abstract_inverted_index.embedding | 136 |
| abstract_inverted_index.features. | 100 |
| abstract_inverted_index.framework | 83 |
| abstract_inverted_index.intensive | 58 |
| abstract_inverted_index.introduce | 77 |
| abstract_inverted_index.potential | 203 |
| abstract_inverted_index.rendering | 121, 175 |
| abstract_inverted_index.requiring | 97 |
| abstract_inverted_index.surpasses | 186 |
| abstract_inverted_index.two-stage | 151 |
| abstract_inverted_index.Splatting, | 80 |
| abstract_inverted_index.accurately | 21 |
| abstract_inverted_index.approaches | 54 |
| abstract_inverted_index.compresses | 155 |
| abstract_inverted_index.dimensions | 161 |
| abstract_inverted_index.efficiency | 199 |
| abstract_inverted_index.generating | 140 |
| abstract_inverted_index.preserving | 163 |
| abstract_inverted_index.real-time, | 88 |
| abstract_inverted_index.seamlessly | 6 |
| abstract_inverted_index.capability. | 125 |
| abstract_inverted_index.computation | 117 |
| abstract_inverted_index.efficiently | 106 |
| abstract_inverted_index.integrating | 39 |
| abstract_inverted_index.interactive | 207 |
| abstract_inverted_index.significant | 36 |
| abstract_inverted_index.Experimental | 177 |
| abstract_inverted_index.adaptability | 69 |
| abstract_inverted_index.auto-encoder | 153 |
| abstract_inverted_index.disentangled | 170 |
| abstract_inverted_index.innovatively | 130 |
| abstract_inverted_index.optimization | 171 |
| abstract_inverted_index.applications. | 209 |
| abstract_inverted_index.capabilities, | 165 |
| abstract_inverted_index.demonstrating | 201 |
| abstract_inverted_index.environments, | 12 |
| abstract_inverted_index.environments. | 72 |
| abstract_inverted_index.geometrically | 43 |
| abstract_inverted_index.pre-generated | 98 |
| abstract_inverted_index.preprocessing | 60 |
| abstract_inverted_index.color-language | 169 |
| abstract_inverted_index.768-dimensional | 156 |
| abstract_inverted_index.computationally | 57 |
| abstract_inverted_index.high-resolution | 134 |
| abstract_inverted_index.open-vocabulary | 89, 124, 164 |
| abstract_inverted_index.representations | 47, 113 |
| abstract_inverted_index.high-dimensional | 108 |
| abstract_inverted_index.representations. | 30 |
| abstract_inverted_index.state-of-the-art | 188 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |