Fine-Tuning Image-Conditional Diffusion Models is Easier than you Think Article Swipe
Glenn Garcia
,
Karim Abou Zeid
,
Christian Schmidt
,
Daan de Geus
,
Alexander Hermans
,
Bastian Leibe
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1109/wacv61041.2025.00083
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1109/wacv61041.2025.00083
Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task. While the proposed model achieved state-of-the-art results, high computational demands due to multi-step inference limited its use in many scenarios. In this paper, we show that the perceived inefficiency was caused by a flaw in the inference pipeline that has so far gone unnoticed. The fixed model performs comparably to the best previously reported configuration while being more than 200x faster. To optimize for downstream task performance, we perform end-to-end fine-tuning on top of the single-step model with task-specific losses and get a deterministic model that outperforms all other diffusion-based depth and normal estimation models on common zero-shot benchmarks. We surprisingly find that this fine-tuning protocol also works directly on Stable Diffusion and achieves comparable performance to current state-of-the-art diffusion-based depth and normal estimation models, calling into question some of the conclusions drawn from prior works.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1109/wacv61041.2025.00083
- OA Status
- gold
- Cited By
- 7
- References
- 42
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4409262827
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4409262827Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/wacv61041.2025.00083Digital Object Identifier
- Title
-
Fine-Tuning Image-Conditional Diffusion Models is Easier than you ThinkWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-02-26Full publication date if available
- Authors
-
Glenn Garcia, Karim Abou Zeid, Christian Schmidt, Daan de Geus, Alexander Hermans, Bastian LeibeList of authors in order
- Landing page
-
https://doi.org/10.1109/wacv61041.2025.00083Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://research.tue.nl/en/publications/bf3fb415-6059-4e06-8351-31728a73ef35Direct OA link when available
- Concepts
-
Computer science, Diffusion, Image (mathematics), Artificial intelligence, Computer vision, Computer graphics (images), Physics, ThermodynamicsTop 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)
- References (count)
-
42Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4409262827 |
|---|---|
| doi | https://doi.org/10.1109/wacv61041.2025.00083 |
| ids.doi | https://doi.org/10.1109/wacv61041.2025.00083 |
| ids.openalex | https://openalex.org/W4409262827 |
| fwci | 32.43776375 |
| type | article |
| title | Fine-Tuning Image-Conditional Diffusion Models is Easier than you Think |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 762 |
| biblio.first_page | 753 |
| topics[0].id | https://openalex.org/T10522 |
| topics[0].field.id | https://openalex.org/fields/27 |
| topics[0].field.display_name | Medicine |
| topics[0].score | 0.7268000245094299 |
| topics[0].domain.id | https://openalex.org/domains/4 |
| topics[0].domain.display_name | Health Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2741 |
| topics[0].subfield.display_name | Radiology, Nuclear Medicine and Imaging |
| topics[0].display_name | Medical Imaging Techniques and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.6452233791351318 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C69357855 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5518471002578735 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q163214 |
| concepts[1].display_name | Diffusion |
| concepts[2].id | https://openalex.org/C115961682 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5453336834907532 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[2].display_name | Image (mathematics) |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.4256453514099121 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C31972630 |
| concepts[4].level | 1 |
| concepts[4].score | 0.37631845474243164 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[4].display_name | Computer vision |
| concepts[5].id | https://openalex.org/C121684516 |
| concepts[5].level | 1 |
| concepts[5].score | 0.34615635871887207 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q7600677 |
| concepts[5].display_name | Computer graphics (images) |
| concepts[6].id | https://openalex.org/C121332964 |
| concepts[6].level | 0 |
| concepts[6].score | 0.08678919076919556 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[6].display_name | Physics |
| concepts[7].id | https://openalex.org/C97355855 |
| concepts[7].level | 1 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11473 |
| concepts[7].display_name | Thermodynamics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.6452233791351318 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/diffusion |
| keywords[1].score | 0.5518471002578735 |
| keywords[1].display_name | Diffusion |
| keywords[2].id | https://openalex.org/keywords/image |
| keywords[2].score | 0.5453336834907532 |
| keywords[2].display_name | Image (mathematics) |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.4256453514099121 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/computer-vision |
| keywords[4].score | 0.37631845474243164 |
| keywords[4].display_name | Computer vision |
| keywords[5].id | https://openalex.org/keywords/computer-graphics |
| keywords[5].score | 0.34615635871887207 |
| keywords[5].display_name | Computer graphics (images) |
| keywords[6].id | https://openalex.org/keywords/physics |
| keywords[6].score | 0.08678919076919556 |
| keywords[6].display_name | Physics |
| language | en |
| locations[0].id | doi:10.1109/wacv61041.2025.00083 |
| locations[0].is_oa | False |
| locations[0].source | |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) |
| locations[0].landing_page_url | https://doi.org/10.1109/wacv61041.2025.00083 |
| locations[1].id | pmh:oai:pure.tue.nl:openaire/bf3fb415-6059-4e06-8351-31728a73ef35 |
| locations[1].is_oa | True |
| locations[1].source | |
| locations[1].license | other-oa |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | contributionToPeriodical |
| locations[1].license_id | https://openalex.org/licenses/other-oa |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | Martin Garcia, G, Abou Zeid, K, Schmidt, C, de Geus, D, Hermans, A & Leibe, B 2025, Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think. in 2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025., 10943344, Institute of Electrical and Electronics Engineers, pp. 753-762, 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, United States, 26/02/25. https://doi.org/10.1109/WACV61041.2025.00083 |
| locations[1].landing_page_url | https://research.tue.nl/en/publications/bf3fb415-6059-4e06-8351-31728a73ef35 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5111868737 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Glenn Garcia |
| authorships[0].countries | DE |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I887968799 |
| authorships[0].affiliations[0].raw_affiliation_string | RWTH Aachen University |
| authorships[0].institutions[0].id | https://openalex.org/I887968799 |
| authorships[0].institutions[0].ror | https://ror.org/04xfq0f34 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I887968799 |
| authorships[0].institutions[0].country_code | DE |
| authorships[0].institutions[0].display_name | RWTH Aachen University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Gonzalo Martin Garcia |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | RWTH Aachen University |
| authorships[1].author.id | https://openalex.org/A5044241033 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Karim Abou Zeid |
| authorships[1].countries | DE |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I887968799 |
| authorships[1].affiliations[0].raw_affiliation_string | RWTH Aachen University |
| authorships[1].institutions[0].id | https://openalex.org/I887968799 |
| authorships[1].institutions[0].ror | https://ror.org/04xfq0f34 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I887968799 |
| authorships[1].institutions[0].country_code | DE |
| authorships[1].institutions[0].display_name | RWTH Aachen University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Karim Abou Zeid |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | RWTH Aachen University |
| authorships[2].author.id | https://openalex.org/A5103544331 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Christian Schmidt |
| authorships[2].countries | DE |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I887968799 |
| authorships[2].affiliations[0].raw_affiliation_string | RWTH Aachen University |
| authorships[2].institutions[0].id | https://openalex.org/I887968799 |
| authorships[2].institutions[0].ror | https://ror.org/04xfq0f34 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I887968799 |
| authorships[2].institutions[0].country_code | DE |
| authorships[2].institutions[0].display_name | RWTH Aachen University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Christian Schmidt |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | RWTH Aachen University |
| authorships[3].author.id | https://openalex.org/A5061463972 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-0559-5341 |
| authorships[3].author.display_name | Daan de Geus |
| authorships[3].countries | DE |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I887968799 |
| authorships[3].affiliations[0].raw_affiliation_string | RWTH Aachen University |
| authorships[3].institutions[0].id | https://openalex.org/I887968799 |
| authorships[3].institutions[0].ror | https://ror.org/04xfq0f34 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I887968799 |
| authorships[3].institutions[0].country_code | DE |
| authorships[3].institutions[0].display_name | RWTH Aachen University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Daan De Geus |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | RWTH Aachen University |
| authorships[4].author.id | https://openalex.org/A5071563379 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-2127-0782 |
| authorships[4].author.display_name | Alexander Hermans |
| authorships[4].countries | DE |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I887968799 |
| authorships[4].affiliations[0].raw_affiliation_string | RWTH Aachen University |
| authorships[4].institutions[0].id | https://openalex.org/I887968799 |
| authorships[4].institutions[0].ror | https://ror.org/04xfq0f34 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I887968799 |
| authorships[4].institutions[0].country_code | DE |
| authorships[4].institutions[0].display_name | RWTH Aachen University |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Alexander Hermans |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | RWTH Aachen University |
| authorships[5].author.id | https://openalex.org/A5071006649 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-4225-0051 |
| authorships[5].author.display_name | Bastian Leibe |
| authorships[5].countries | DE |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I887968799 |
| authorships[5].affiliations[0].raw_affiliation_string | RWTH Aachen University |
| authorships[5].institutions[0].id | https://openalex.org/I887968799 |
| authorships[5].institutions[0].ror | https://ror.org/04xfq0f34 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I887968799 |
| authorships[5].institutions[0].country_code | DE |
| authorships[5].institutions[0].display_name | RWTH Aachen University |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Bastian Leibe |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | RWTH Aachen University |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://research.tue.nl/en/publications/bf3fb415-6059-4e06-8351-31728a73ef35 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Fine-Tuning Image-Conditional Diffusion Models is Easier than you Think |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10522 |
| primary_topic.field.id | https://openalex.org/fields/27 |
| primary_topic.field.display_name | Medicine |
| primary_topic.score | 0.7268000245094299 |
| primary_topic.domain.id | https://openalex.org/domains/4 |
| primary_topic.domain.display_name | Health Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2741 |
| primary_topic.subfield.display_name | Radiology, Nuclear Medicine and Imaging |
| primary_topic.display_name | Medical Imaging Techniques and Applications |
| related_works | https://openalex.org/W2772917594, https://openalex.org/W2036807459, https://openalex.org/W2058170566, https://openalex.org/W2755342338, https://openalex.org/W2166024367, https://openalex.org/W3116076068, https://openalex.org/W2229312674, https://openalex.org/W2951359407, https://openalex.org/W2079911747, https://openalex.org/W1969923398 |
| 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:pure.tue.nl:openaire/bf3fb415-6059-4e06-8351-31728a73ef35 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | other-oa |
| best_oa_location.pdf_url | |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | contributionToPeriodical |
| best_oa_location.license_id | https://openalex.org/licenses/other-oa |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | Martin Garcia, G, Abou Zeid, K, Schmidt, C, de Geus, D, Hermans, A & Leibe, B 2025, Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think. in 2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025., 10943344, Institute of Electrical and Electronics Engineers, pp. 753-762, 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, United States, 26/02/25. https://doi.org/10.1109/WACV61041.2025.00083 |
| best_oa_location.landing_page_url | https://research.tue.nl/en/publications/bf3fb415-6059-4e06-8351-31728a73ef35 |
| primary_location.id | doi:10.1109/wacv61041.2025.00083 |
| primary_location.is_oa | False |
| primary_location.source | |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) |
| primary_location.landing_page_url | https://doi.org/10.1109/wacv61041.2025.00083 |
| publication_date | 2025-02-26 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W3199238138, https://openalex.org/W4402753900, https://openalex.org/W2962809185, https://openalex.org/W1513100184, https://openalex.org/W2594519801, https://openalex.org/W4403947105, https://openalex.org/W3203887644, https://openalex.org/W6639633739, https://openalex.org/W6862238593, https://openalex.org/W2150066425, https://openalex.org/W6779823529, https://openalex.org/W2151996626, https://openalex.org/W2125310925, https://openalex.org/W4395481595, https://openalex.org/W4312388311, https://openalex.org/W6838452192, https://openalex.org/W4402753888, https://openalex.org/W6750474155, https://openalex.org/W2963760790, https://openalex.org/W4394625831, https://openalex.org/W6846539466, https://openalex.org/W4402733585, https://openalex.org/W6757817989, https://openalex.org/W4402727115, https://openalex.org/W4402754301, https://openalex.org/W4214520160, https://openalex.org/W6782298681, https://openalex.org/W3097660860, https://openalex.org/W4312933868, https://openalex.org/W6809884996, https://openalex.org/W6853818442, https://openalex.org/W2741885505, https://openalex.org/W125693051, https://openalex.org/W6783713337, https://openalex.org/W1899309388, https://openalex.org/W4402727359, https://openalex.org/W6791436909, https://openalex.org/W4390871919, https://openalex.org/W3174458495, https://openalex.org/W6849845829, https://openalex.org/W4390873429, https://openalex.org/W6854302227 |
| referenced_works_count | 42 |
| abstract_inverted_index.a | 58, 108 |
| abstract_inverted_index.In | 46 |
| abstract_inverted_index.To | 87 |
| abstract_inverted_index.We | 125 |
| abstract_inverted_index.an | 21 |
| abstract_inverted_index.as | 10, 20 |
| abstract_inverted_index.be | 8 |
| abstract_inverted_index.by | 16, 57 |
| abstract_inverted_index.in | 43, 60 |
| abstract_inverted_index.of | 99, 155 |
| abstract_inverted_index.on | 97, 121, 135 |
| abstract_inverted_index.so | 66 |
| abstract_inverted_index.to | 37, 75, 142 |
| abstract_inverted_index.we | 49, 93 |
| abstract_inverted_index.The | 70 |
| abstract_inverted_index.all | 113 |
| abstract_inverted_index.and | 106, 117, 138, 147 |
| abstract_inverted_index.can | 7 |
| abstract_inverted_index.due | 36 |
| abstract_inverted_index.far | 67 |
| abstract_inverted_index.for | 89 |
| abstract_inverted_index.get | 107 |
| abstract_inverted_index.has | 65 |
| abstract_inverted_index.its | 41 |
| abstract_inverted_index.the | 27, 52, 61, 76, 100, 156 |
| abstract_inverted_index.top | 98 |
| abstract_inverted_index.use | 42 |
| abstract_inverted_index.was | 55 |
| abstract_inverted_index.200x | 85 |
| abstract_inverted_index.also | 132 |
| abstract_inverted_index.best | 77 |
| abstract_inverted_index.find | 127 |
| abstract_inverted_index.flaw | 59 |
| abstract_inverted_index.from | 159 |
| abstract_inverted_index.gone | 68 |
| abstract_inverted_index.high | 33 |
| abstract_inverted_index.into | 152 |
| abstract_inverted_index.many | 44 |
| abstract_inverted_index.more | 83 |
| abstract_inverted_index.show | 50 |
| abstract_inverted_index.some | 154 |
| abstract_inverted_index.task | 91 |
| abstract_inverted_index.than | 84 |
| abstract_inverted_index.that | 3, 51, 64, 111, 128 |
| abstract_inverted_index.this | 47, 129 |
| abstract_inverted_index.with | 103 |
| abstract_inverted_index.work | 1 |
| abstract_inverted_index.While | 26 |
| abstract_inverted_index.being | 82 |
| abstract_inverted_index.depth | 14, 18, 116, 146 |
| abstract_inverted_index.drawn | 158 |
| abstract_inverted_index.fixed | 71 |
| abstract_inverted_index.image | 23 |
| abstract_inverted_index.large | 4 |
| abstract_inverted_index.model | 29, 72, 102, 110 |
| abstract_inverted_index.other | 114 |
| abstract_inverted_index.prior | 160 |
| abstract_inverted_index.task. | 25 |
| abstract_inverted_index.while | 81 |
| abstract_inverted_index.works | 133 |
| abstract_inverted_index.Recent | 0 |
| abstract_inverted_index.Stable | 136 |
| abstract_inverted_index.caused | 56 |
| abstract_inverted_index.common | 122 |
| abstract_inverted_index.highly | 11 |
| abstract_inverted_index.losses | 105 |
| abstract_inverted_index.models | 6, 120 |
| abstract_inverted_index.normal | 118, 148 |
| abstract_inverted_index.paper, | 48 |
| abstract_inverted_index.reused | 9 |
| abstract_inverted_index.showed | 2 |
| abstract_inverted_index.works. | 161 |
| abstract_inverted_index.calling | 151 |
| abstract_inverted_index.casting | 17 |
| abstract_inverted_index.current | 143 |
| abstract_inverted_index.demands | 35 |
| abstract_inverted_index.faster. | 86 |
| abstract_inverted_index.limited | 40 |
| abstract_inverted_index.models, | 150 |
| abstract_inverted_index.perform | 94 |
| abstract_inverted_index.precise | 12 |
| abstract_inverted_index.achieved | 30 |
| abstract_inverted_index.achieves | 139 |
| abstract_inverted_index.directly | 134 |
| abstract_inverted_index.optimize | 88 |
| abstract_inverted_index.performs | 73 |
| abstract_inverted_index.pipeline | 63 |
| abstract_inverted_index.proposed | 28 |
| abstract_inverted_index.protocol | 131 |
| abstract_inverted_index.question | 153 |
| abstract_inverted_index.reported | 79 |
| abstract_inverted_index.results, | 32 |
| abstract_inverted_index.Diffusion | 137 |
| abstract_inverted_index.diffusion | 5 |
| abstract_inverted_index.inference | 39, 62 |
| abstract_inverted_index.monocular | 13 |
| abstract_inverted_index.perceived | 53 |
| abstract_inverted_index.zero-shot | 123 |
| abstract_inverted_index.comparable | 140 |
| abstract_inverted_index.comparably | 74 |
| abstract_inverted_index.downstream | 90 |
| abstract_inverted_index.end-to-end | 95 |
| abstract_inverted_index.estimation | 19, 119, 149 |
| abstract_inverted_index.estimators | 15 |
| abstract_inverted_index.generation | 24 |
| abstract_inverted_index.multi-step | 38 |
| abstract_inverted_index.previously | 78 |
| abstract_inverted_index.scenarios. | 45 |
| abstract_inverted_index.unnoticed. | 69 |
| abstract_inverted_index.benchmarks. | 124 |
| abstract_inverted_index.conclusions | 157 |
| abstract_inverted_index.fine-tuning | 96, 130 |
| abstract_inverted_index.outperforms | 112 |
| abstract_inverted_index.performance | 141 |
| abstract_inverted_index.single-step | 101 |
| abstract_inverted_index.inefficiency | 54 |
| abstract_inverted_index.performance, | 92 |
| abstract_inverted_index.surprisingly | 126 |
| abstract_inverted_index.computational | 34 |
| abstract_inverted_index.configuration | 80 |
| abstract_inverted_index.deterministic | 109 |
| abstract_inverted_index.task-specific | 104 |
| abstract_inverted_index.diffusion-based | 115, 145 |
| abstract_inverted_index.state-of-the-art | 31, 144 |
| abstract_inverted_index.image-conditional | 22 |
| cited_by_percentile_year.max | 99 |
| cited_by_percentile_year.min | 98 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile.value | 0.99259904 |
| citation_normalized_percentile.is_in_top_1_percent | True |
| citation_normalized_percentile.is_in_top_10_percent | True |