A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D Article Swipe
Xiaohan Fei
,
Chethan M. Parameshwara
,
Jiawei Mo
,
Xiaolong Li
,
Ashwin Swaminathan
,
Chris Taylor
,
Paolo Favaro
,
Stefano Soatto
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2402.18780
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2402.18780
The development of generative models that create 3D content from a text prompt has made considerable strides thanks to the use of the score distillation sampling (SDS) method on pre-trained diffusion models for image generation. However, the SDS method is also the source of several artifacts, such as the Janus problem, the misalignment between the text prompt and the generated 3D model, and 3D model inaccuracies. While existing methods heavily rely on the qualitative assessment of these artifacts through visual inspection of a limited set of samples, in this work we propose more objective quantitative evaluation metrics, which we cross-validate via human ratings, and show analysis of the failure cases of the SDS technique. We demonstrate the effectiveness of this analysis by designing a novel computationally efficient baseline model that achieves state-of-the-art performance on the proposed metrics while addressing all the above-mentioned artifacts.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2402.18780
- https://arxiv.org/pdf/2402.18780
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4401066009
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4401066009Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2402.18780Digital Object Identifier
- Title
-
A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3DWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-02-29Full publication date if available
- Authors
-
Xiaohan Fei, Chethan M. Parameshwara, Jiawei Mo, Xiaolong Li, Ashwin Swaminathan, Chris Taylor, Paolo Favaro, Stefano SoattoList of authors in order
- Landing page
-
https://arxiv.org/abs/2402.18780Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2402.18780Direct 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/2402.18780Direct OA link when available
- Concepts
-
Sampling (signal processing), Distillation, Statistics, Computer science, Natural language processing, Econometrics, Artificial intelligence, Mathematics, Environmental science, Chromatography, Chemistry, Filter (signal processing), Computer visionTop 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/W4401066009 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2402.18780 |
| ids.doi | https://doi.org/10.48550/arxiv.2402.18780 |
| ids.openalex | https://openalex.org/W4401066009 |
| fwci | |
| type | preprint |
| title | A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11309 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.3264000117778778 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1711 |
| topics[0].subfield.display_name | Signal Processing |
| topics[0].display_name | Music and Audio Processing |
| topics[1].id | https://openalex.org/T13083 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.2930999994277954 |
| 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 | Advanced Text Analysis Techniques |
| topics[2].id | https://openalex.org/T13910 |
| topics[2].field.id | https://openalex.org/fields/33 |
| topics[2].field.display_name | Social Sciences |
| topics[2].score | 0.27320000529289246 |
| topics[2].domain.id | https://openalex.org/domains/2 |
| topics[2].domain.display_name | Social Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/3300 |
| topics[2].subfield.display_name | General Social Sciences |
| topics[2].display_name | Computational and Text Analysis Methods |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C140779682 |
| concepts[0].level | 3 |
| concepts[0].score | 0.6147405505180359 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q210868 |
| concepts[0].display_name | Sampling (signal processing) |
| concepts[1].id | https://openalex.org/C204030448 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6082916259765625 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q101017 |
| concepts[1].display_name | Distillation |
| concepts[2].id | https://openalex.org/C105795698 |
| concepts[2].level | 1 |
| concepts[2].score | 0.4835650622844696 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[2].display_name | Statistics |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.4246235489845276 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C204321447 |
| concepts[4].level | 1 |
| concepts[4].score | 0.3970583975315094 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[4].display_name | Natural language processing |
| concepts[5].id | https://openalex.org/C149782125 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3452598452568054 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q160039 |
| concepts[5].display_name | Econometrics |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.34423696994781494 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C33923547 |
| concepts[7].level | 0 |
| concepts[7].score | 0.33156198263168335 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[7].display_name | Mathematics |
| concepts[8].id | https://openalex.org/C39432304 |
| concepts[8].level | 0 |
| concepts[8].score | 0.32460683584213257 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q188847 |
| concepts[8].display_name | Environmental science |
| concepts[9].id | https://openalex.org/C43617362 |
| concepts[9].level | 1 |
| concepts[9].score | 0.22878959774971008 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q170050 |
| concepts[9].display_name | Chromatography |
| concepts[10].id | https://openalex.org/C185592680 |
| concepts[10].level | 0 |
| concepts[10].score | 0.140153169631958 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[10].display_name | Chemistry |
| concepts[11].id | https://openalex.org/C106131492 |
| concepts[11].level | 2 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q3072260 |
| concepts[11].display_name | Filter (signal processing) |
| concepts[12].id | https://openalex.org/C31972630 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[12].display_name | Computer vision |
| keywords[0].id | https://openalex.org/keywords/sampling |
| keywords[0].score | 0.6147405505180359 |
| keywords[0].display_name | Sampling (signal processing) |
| keywords[1].id | https://openalex.org/keywords/distillation |
| keywords[1].score | 0.6082916259765625 |
| keywords[1].display_name | Distillation |
| keywords[2].id | https://openalex.org/keywords/statistics |
| keywords[2].score | 0.4835650622844696 |
| keywords[2].display_name | Statistics |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.4246235489845276 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/natural-language-processing |
| keywords[4].score | 0.3970583975315094 |
| keywords[4].display_name | Natural language processing |
| keywords[5].id | https://openalex.org/keywords/econometrics |
| keywords[5].score | 0.3452598452568054 |
| keywords[5].display_name | Econometrics |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.34423696994781494 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/mathematics |
| keywords[7].score | 0.33156198263168335 |
| keywords[7].display_name | Mathematics |
| keywords[8].id | https://openalex.org/keywords/environmental-science |
| keywords[8].score | 0.32460683584213257 |
| keywords[8].display_name | Environmental science |
| keywords[9].id | https://openalex.org/keywords/chromatography |
| keywords[9].score | 0.22878959774971008 |
| keywords[9].display_name | Chromatography |
| keywords[10].id | https://openalex.org/keywords/chemistry |
| keywords[10].score | 0.140153169631958 |
| keywords[10].display_name | Chemistry |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2402.18780 |
| 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/2402.18780 |
| 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/2402.18780 |
| locations[1].id | doi:10.48550/arxiv.2402.18780 |
| 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.2402.18780 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5087030407 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-1030-2286 |
| authorships[0].author.display_name | Xiaohan Fei |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Fei, Xiaohan |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5075055783 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Chethan M. Parameshwara |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Parameshwara, Chethan |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5087799311 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-1043-5353 |
| authorships[2].author.display_name | Jiawei Mo |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Mo, Jiawei |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100371535 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-7493-2650 |
| authorships[3].author.display_name | Xiaolong Li |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Li, Xiaolong |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5084355679 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-4279-369X |
| authorships[4].author.display_name | Ashwin Swaminathan |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Swaminathan, Ashwin |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5067224766 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-7867-9533 |
| authorships[5].author.display_name | Chris Taylor |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Taylor, CJ |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5070940574 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-3546-8247 |
| authorships[6].author.display_name | Paolo Favaro |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Favaro, Paolo |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5038328783 |
| authorships[7].author.orcid | https://orcid.org/0000-0003-2902-6362 |
| authorships[7].author.display_name | Stefano Soatto |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Soatto, Stefano |
| authorships[7].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/2402.18780 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-07-31T00:00:00 |
| display_name | A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11309 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.3264000117778778 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1711 |
| primary_topic.subfield.display_name | Signal Processing |
| primary_topic.display_name | Music and Audio Processing |
| related_works | https://openalex.org/W3026162553, https://openalex.org/W2768175398, https://openalex.org/W1922851888, https://openalex.org/W2344382886, https://openalex.org/W19111321, https://openalex.org/W2412887479, https://openalex.org/W32245304, https://openalex.org/W2953684491, https://openalex.org/W4285338581, https://openalex.org/W3107697994 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2402.18780 |
| 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/2402.18780 |
| 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/2402.18780 |
| primary_location.id | pmh:oai:arXiv.org:2402.18780 |
| 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/2402.18780 |
| 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/2402.18780 |
| publication_date | 2024-02-29 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 10, 82, 123 |
| abstract_inverted_index.3D | 7, 60, 63 |
| abstract_inverted_index.We | 114 |
| abstract_inverted_index.as | 47 |
| abstract_inverted_index.by | 121 |
| abstract_inverted_index.in | 87 |
| abstract_inverted_index.is | 39 |
| abstract_inverted_index.of | 2, 21, 43, 75, 81, 85, 106, 110, 118 |
| abstract_inverted_index.on | 28, 71, 133 |
| abstract_inverted_index.to | 18 |
| abstract_inverted_index.we | 90, 98 |
| abstract_inverted_index.SDS | 37, 112 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.all | 139 |
| abstract_inverted_index.and | 57, 62, 103 |
| abstract_inverted_index.for | 32 |
| abstract_inverted_index.has | 13 |
| abstract_inverted_index.set | 84 |
| abstract_inverted_index.the | 19, 22, 36, 41, 48, 51, 54, 58, 72, 107, 111, 116, 134, 140 |
| abstract_inverted_index.use | 20 |
| abstract_inverted_index.via | 100 |
| abstract_inverted_index.also | 40 |
| abstract_inverted_index.from | 9 |
| abstract_inverted_index.made | 14 |
| abstract_inverted_index.more | 92 |
| abstract_inverted_index.rely | 70 |
| abstract_inverted_index.show | 104 |
| abstract_inverted_index.such | 46 |
| abstract_inverted_index.text | 11, 55 |
| abstract_inverted_index.that | 5, 129 |
| abstract_inverted_index.this | 88, 119 |
| abstract_inverted_index.work | 89 |
| abstract_inverted_index.(SDS) | 26 |
| abstract_inverted_index.Janus | 49 |
| abstract_inverted_index.While | 66 |
| abstract_inverted_index.cases | 109 |
| abstract_inverted_index.human | 101 |
| abstract_inverted_index.image | 33 |
| abstract_inverted_index.model | 64, 128 |
| abstract_inverted_index.novel | 124 |
| abstract_inverted_index.score | 23 |
| abstract_inverted_index.these | 76 |
| abstract_inverted_index.which | 97 |
| abstract_inverted_index.while | 137 |
| abstract_inverted_index.create | 6 |
| abstract_inverted_index.method | 27, 38 |
| abstract_inverted_index.model, | 61 |
| abstract_inverted_index.models | 4, 31 |
| abstract_inverted_index.prompt | 12, 56 |
| abstract_inverted_index.source | 42 |
| abstract_inverted_index.thanks | 17 |
| abstract_inverted_index.visual | 79 |
| abstract_inverted_index.between | 53 |
| abstract_inverted_index.content | 8 |
| abstract_inverted_index.failure | 108 |
| abstract_inverted_index.heavily | 69 |
| abstract_inverted_index.limited | 83 |
| abstract_inverted_index.methods | 68 |
| abstract_inverted_index.metrics | 136 |
| abstract_inverted_index.propose | 91 |
| abstract_inverted_index.several | 44 |
| abstract_inverted_index.strides | 16 |
| abstract_inverted_index.through | 78 |
| abstract_inverted_index.However, | 35 |
| abstract_inverted_index.achieves | 130 |
| abstract_inverted_index.analysis | 105, 120 |
| abstract_inverted_index.baseline | 127 |
| abstract_inverted_index.existing | 67 |
| abstract_inverted_index.metrics, | 96 |
| abstract_inverted_index.problem, | 50 |
| abstract_inverted_index.proposed | 135 |
| abstract_inverted_index.ratings, | 102 |
| abstract_inverted_index.samples, | 86 |
| abstract_inverted_index.sampling | 25 |
| abstract_inverted_index.artifacts | 77 |
| abstract_inverted_index.designing | 122 |
| abstract_inverted_index.diffusion | 30 |
| abstract_inverted_index.efficient | 126 |
| abstract_inverted_index.generated | 59 |
| abstract_inverted_index.objective | 93 |
| abstract_inverted_index.addressing | 138 |
| abstract_inverted_index.artifacts, | 45 |
| abstract_inverted_index.artifacts. | 142 |
| abstract_inverted_index.assessment | 74 |
| abstract_inverted_index.evaluation | 95 |
| abstract_inverted_index.generative | 3 |
| abstract_inverted_index.inspection | 80 |
| abstract_inverted_index.technique. | 113 |
| abstract_inverted_index.demonstrate | 115 |
| abstract_inverted_index.development | 1 |
| abstract_inverted_index.generation. | 34 |
| abstract_inverted_index.performance | 132 |
| abstract_inverted_index.pre-trained | 29 |
| abstract_inverted_index.qualitative | 73 |
| abstract_inverted_index.considerable | 15 |
| abstract_inverted_index.distillation | 24 |
| abstract_inverted_index.misalignment | 52 |
| abstract_inverted_index.quantitative | 94 |
| abstract_inverted_index.effectiveness | 117 |
| abstract_inverted_index.inaccuracies. | 65 |
| abstract_inverted_index.cross-validate | 99 |
| abstract_inverted_index.above-mentioned | 141 |
| abstract_inverted_index.computationally | 125 |
| abstract_inverted_index.state-of-the-art | 131 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile |