GenesisTex2: Stable, Consistent and High-Quality Text-to-Texture Generation Article Swipe
Jiawei Lu
,
Yingpeng Zhang
,
Zengjun Zhao
,
He Wang
,
Kun Zhou
,
Tianjia Shao
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2409.18401
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2409.18401
Large-scale text-guided image diffusion models have shown astonishing results in text-to-image (T2I) generation. However, applying these models to synthesize textures for 3D geometries remains challenging due to the domain gap between 2D images and textures on a 3D surface. Early works that used a projecting-and-inpainting approach managed to preserve generation diversity but often resulted in noticeable artifacts and style inconsistencies. While recent methods have attempted to address these inconsistencies, they often introduce other issues, such as blurring, over-saturation, or over-smoothing. To overcome these challenges, we propose a novel text-to-texture synthesis framework that leverages pretrained diffusion models. We first introduce a local attention reweighing mechanism in the self-attention layers to guide the model in concentrating on spatial-correlated patches across different views, thereby enhancing local details while preserving cross-view consistency. Additionally, we propose a novel latent space merge pipeline, which further ensures consistency across different viewpoints without sacrificing too much diversity. Our method significantly outperforms existing state-of-the-art techniques regarding texture consistency and visual quality, while delivering results much faster than distillation-based methods. Importantly, our framework does not require additional training or fine-tuning, making it highly adaptable to a wide range of models available on public platforms.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2409.18401
- https://arxiv.org/pdf/2409.18401
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4403809276
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4403809276Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2409.18401Digital Object Identifier
- Title
-
GenesisTex2: Stable, Consistent and High-Quality Text-to-Texture GenerationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-09-27Full publication date if available
- Authors
-
Jiawei Lu, Yingpeng Zhang, Zengjun Zhao, He Wang, Kun Zhou, Tianjia ShaoList of authors in order
- Landing page
-
https://arxiv.org/abs/2409.18401Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2409.18401Direct 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/2409.18401Direct OA link when available
- Concepts
-
Texture (cosmology), Quality (philosophy), Computer science, Artificial intelligence, Physics, Image (mathematics), Quantum mechanicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4403809276 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2409.18401 |
| ids.doi | https://doi.org/10.48550/arxiv.2409.18401 |
| ids.openalex | https://openalex.org/W4403809276 |
| fwci | |
| type | preprint |
| title | GenesisTex2: Stable, Consistent and High-Quality Text-to-Texture Generation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10181 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.929099977016449 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Natural Language Processing Techniques |
| topics[1].id | https://openalex.org/T10601 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9032999873161316 |
| 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 | Handwritten Text Recognition Techniques |
| topics[2].id | https://openalex.org/T10028 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9027000069618225 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Topic Modeling |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2781195486 |
| concepts[0].level | 3 |
| concepts[0].score | 0.7081027626991272 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q289436 |
| concepts[0].display_name | Texture (cosmology) |
| concepts[1].id | https://openalex.org/C2779530757 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5673488974571228 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1207505 |
| concepts[1].display_name | Quality (philosophy) |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.42683643102645874 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.3343241214752197 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C121332964 |
| concepts[4].level | 0 |
| concepts[4].score | 0.13408821821212769 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[4].display_name | Physics |
| concepts[5].id | https://openalex.org/C115961682 |
| concepts[5].level | 2 |
| concepts[5].score | 0.05970805883407593 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[5].display_name | Image (mathematics) |
| concepts[6].id | https://openalex.org/C62520636 |
| concepts[6].level | 1 |
| concepts[6].score | 0.0 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[6].display_name | Quantum mechanics |
| keywords[0].id | https://openalex.org/keywords/texture |
| keywords[0].score | 0.7081027626991272 |
| keywords[0].display_name | Texture (cosmology) |
| keywords[1].id | https://openalex.org/keywords/quality |
| keywords[1].score | 0.5673488974571228 |
| keywords[1].display_name | Quality (philosophy) |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.42683643102645874 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.3343241214752197 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/physics |
| keywords[4].score | 0.13408821821212769 |
| keywords[4].display_name | Physics |
| keywords[5].id | https://openalex.org/keywords/image |
| keywords[5].score | 0.05970805883407593 |
| keywords[5].display_name | Image (mathematics) |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2409.18401 |
| 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/2409.18401 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/2409.18401 |
| locations[1].id | doi:10.48550/arxiv.2409.18401 |
| 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.2409.18401 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5071016982 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7229-8887 |
| authorships[0].author.display_name | Jiawei Lu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Lu, Jiawei |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5002132956 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3873-4574 |
| authorships[1].author.display_name | Yingpeng Zhang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zhang, Yingpeng |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5069984737 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Zengjun Zhao |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhao, Zengjun |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5103036847 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-1605-3903 |
| authorships[3].author.display_name | He Wang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Wang, He |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5115603169 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-1726-4697 |
| authorships[4].author.display_name | Kun Zhou |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Zhou, Kun |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5060286507 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-5485-3752 |
| authorships[5].author.display_name | Tianjia Shao |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Shao, Tianjia |
| 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/2409.18401 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-10-28T00:00:00 |
| display_name | GenesisTex2: Stable, Consistent and High-Quality Text-to-Texture Generation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10181 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.929099977016449 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Natural Language Processing Techniques |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2409.18401 |
| 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/2409.18401 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/2409.18401 |
| primary_location.id | pmh:oai:arXiv.org:2409.18401 |
| 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/2409.18401 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/2409.18401 |
| publication_date | 2024-09-27 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 36, 43, 86, 99, 131, 185 |
| abstract_inverted_index.2D | 31 |
| abstract_inverted_index.3D | 21, 37 |
| abstract_inverted_index.To | 80 |
| abstract_inverted_index.We | 96 |
| abstract_inverted_index.as | 75 |
| abstract_inverted_index.in | 9, 54, 104, 112 |
| abstract_inverted_index.it | 181 |
| abstract_inverted_index.of | 188 |
| abstract_inverted_index.on | 35, 114, 191 |
| abstract_inverted_index.or | 78, 178 |
| abstract_inverted_index.to | 17, 26, 47, 65, 108, 184 |
| abstract_inverted_index.we | 84, 129 |
| abstract_inverted_index.Our | 149 |
| abstract_inverted_index.and | 33, 57, 159 |
| abstract_inverted_index.but | 51 |
| abstract_inverted_index.due | 25 |
| abstract_inverted_index.for | 20 |
| abstract_inverted_index.gap | 29 |
| abstract_inverted_index.not | 174 |
| abstract_inverted_index.our | 171 |
| abstract_inverted_index.the | 27, 105, 110 |
| abstract_inverted_index.too | 146 |
| abstract_inverted_index.does | 173 |
| abstract_inverted_index.have | 5, 63 |
| abstract_inverted_index.much | 147, 165 |
| abstract_inverted_index.such | 74 |
| abstract_inverted_index.than | 167 |
| abstract_inverted_index.that | 41, 91 |
| abstract_inverted_index.they | 69 |
| abstract_inverted_index.used | 42 |
| abstract_inverted_index.wide | 186 |
| abstract_inverted_index.(T2I) | 11 |
| abstract_inverted_index.Early | 39 |
| abstract_inverted_index.While | 60 |
| abstract_inverted_index.first | 97 |
| abstract_inverted_index.guide | 109 |
| abstract_inverted_index.image | 2 |
| abstract_inverted_index.local | 100, 122 |
| abstract_inverted_index.merge | 135 |
| abstract_inverted_index.model | 111 |
| abstract_inverted_index.novel | 87, 132 |
| abstract_inverted_index.often | 52, 70 |
| abstract_inverted_index.other | 72 |
| abstract_inverted_index.range | 187 |
| abstract_inverted_index.shown | 6 |
| abstract_inverted_index.space | 134 |
| abstract_inverted_index.style | 58 |
| abstract_inverted_index.these | 15, 67, 82 |
| abstract_inverted_index.which | 137 |
| abstract_inverted_index.while | 124, 162 |
| abstract_inverted_index.works | 40 |
| abstract_inverted_index.across | 117, 141 |
| abstract_inverted_index.domain | 28 |
| abstract_inverted_index.faster | 166 |
| abstract_inverted_index.highly | 182 |
| abstract_inverted_index.images | 32 |
| abstract_inverted_index.latent | 133 |
| abstract_inverted_index.layers | 107 |
| abstract_inverted_index.making | 180 |
| abstract_inverted_index.method | 150 |
| abstract_inverted_index.models | 4, 16, 189 |
| abstract_inverted_index.public | 192 |
| abstract_inverted_index.recent | 61 |
| abstract_inverted_index.views, | 119 |
| abstract_inverted_index.visual | 160 |
| abstract_inverted_index.address | 66 |
| abstract_inverted_index.between | 30 |
| abstract_inverted_index.details | 123 |
| abstract_inverted_index.ensures | 139 |
| abstract_inverted_index.further | 138 |
| abstract_inverted_index.issues, | 73 |
| abstract_inverted_index.managed | 46 |
| abstract_inverted_index.methods | 62 |
| abstract_inverted_index.models. | 95 |
| abstract_inverted_index.patches | 116 |
| abstract_inverted_index.propose | 85, 130 |
| abstract_inverted_index.remains | 23 |
| abstract_inverted_index.require | 175 |
| abstract_inverted_index.results | 8, 164 |
| abstract_inverted_index.texture | 157 |
| abstract_inverted_index.thereby | 120 |
| abstract_inverted_index.without | 144 |
| abstract_inverted_index.However, | 13 |
| abstract_inverted_index.applying | 14 |
| abstract_inverted_index.approach | 45 |
| abstract_inverted_index.existing | 153 |
| abstract_inverted_index.methods. | 169 |
| abstract_inverted_index.overcome | 81 |
| abstract_inverted_index.preserve | 48 |
| abstract_inverted_index.quality, | 161 |
| abstract_inverted_index.resulted | 53 |
| abstract_inverted_index.surface. | 38 |
| abstract_inverted_index.textures | 19, 34 |
| abstract_inverted_index.training | 177 |
| abstract_inverted_index.adaptable | 183 |
| abstract_inverted_index.artifacts | 56 |
| abstract_inverted_index.attempted | 64 |
| abstract_inverted_index.attention | 101 |
| abstract_inverted_index.available | 190 |
| abstract_inverted_index.blurring, | 76 |
| abstract_inverted_index.different | 118, 142 |
| abstract_inverted_index.diffusion | 3, 94 |
| abstract_inverted_index.diversity | 50 |
| abstract_inverted_index.enhancing | 121 |
| abstract_inverted_index.framework | 90, 172 |
| abstract_inverted_index.introduce | 71, 98 |
| abstract_inverted_index.leverages | 92 |
| abstract_inverted_index.mechanism | 103 |
| abstract_inverted_index.pipeline, | 136 |
| abstract_inverted_index.regarding | 156 |
| abstract_inverted_index.synthesis | 89 |
| abstract_inverted_index.additional | 176 |
| abstract_inverted_index.cross-view | 126 |
| abstract_inverted_index.delivering | 163 |
| abstract_inverted_index.diversity. | 148 |
| abstract_inverted_index.generation | 49 |
| abstract_inverted_index.geometries | 22 |
| abstract_inverted_index.noticeable | 55 |
| abstract_inverted_index.platforms. | 193 |
| abstract_inverted_index.preserving | 125 |
| abstract_inverted_index.pretrained | 93 |
| abstract_inverted_index.reweighing | 102 |
| abstract_inverted_index.synthesize | 18 |
| abstract_inverted_index.techniques | 155 |
| abstract_inverted_index.viewpoints | 143 |
| abstract_inverted_index.Large-scale | 0 |
| abstract_inverted_index.astonishing | 7 |
| abstract_inverted_index.challenges, | 83 |
| abstract_inverted_index.challenging | 24 |
| abstract_inverted_index.consistency | 140, 158 |
| abstract_inverted_index.generation. | 12 |
| abstract_inverted_index.outperforms | 152 |
| abstract_inverted_index.sacrificing | 145 |
| abstract_inverted_index.text-guided | 1 |
| abstract_inverted_index.Importantly, | 170 |
| abstract_inverted_index.consistency. | 127 |
| abstract_inverted_index.fine-tuning, | 179 |
| abstract_inverted_index.Additionally, | 128 |
| abstract_inverted_index.concentrating | 113 |
| abstract_inverted_index.significantly | 151 |
| abstract_inverted_index.text-to-image | 10 |
| abstract_inverted_index.self-attention | 106 |
| abstract_inverted_index.over-smoothing. | 79 |
| abstract_inverted_index.text-to-texture | 88 |
| abstract_inverted_index.inconsistencies, | 68 |
| abstract_inverted_index.inconsistencies. | 59 |
| abstract_inverted_index.over-saturation, | 77 |
| abstract_inverted_index.state-of-the-art | 154 |
| abstract_inverted_index.distillation-based | 168 |
| abstract_inverted_index.spatial-correlated | 115 |
| abstract_inverted_index.projecting-and-inpainting | 44 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |