{"id":"https://openalex.org/W4405627739","doi":"https://doi.org/10.1109/iccv51701.2025.01570","title":"DiffSim: Taming Diffusion Models for Evaluating Visual Similarity","display_name":"DiffSim: Taming Diffusion Models for Evaluating Visual Similarity","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405627739","doi":"https://doi.org/10.1109/iccv51701.2025.01570"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.14580","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019405339","display_name":"Yiren Song","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yiren Song","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628113","display_name":"Xiaokang Liu","orcid":"https://orcid.org/0000-0001-8732-0338"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaokang Liu","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mike Zheng Shou","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16904","last_page":"16915"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9689000248908997,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9689000248908997,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9526000022888184,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9140999913215637,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5710112452507019},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.49458619952201843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4807322025299072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4131101667881012},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11189484596252441},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06595692038536072},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.04577574133872986}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5710112452507019},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.49458619952201843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4807322025299072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4131101667881012},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11189484596252441},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06595692038536072},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.04577574133872986}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.14580","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.14580","pdf_url":"https://arxiv.org/pdf/2412.14580","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.14580","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.14580","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.14580","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.14580","pdf_url":"https://arxiv.org/pdf/2412.14580","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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"],"abstract_inverted_index":{"Diffusion":[0],"models":[1,92],"have":[2],"fundamentally":[3],"transformed":[4],"the":[5,11,32,85,102,106,123,127,147,157],"field":[6],"of":[7,13,108,126,159],"generative":[8,184],"models,":[9],"making":[10],"assessment":[12],"similarity":[14,27,99,155],"between":[15],"customized":[16],"model":[17],"outputs":[18],"and":[19,34,40,48,55,61,100,134,149,161],"reference":[20],"inputs":[21],"critically":[22],"important.":[23],"However,":[24],"traditional":[25,109],"perceptual":[26,113],"metrics":[28,110],"operate":[29],"primarily":[30],"at":[31,156],"pixel":[33],"patch":[35],"levels,":[36],"comparing":[37],"low-level":[38],"colors":[39],"textures":[41],"but":[42,72],"failing":[43],"to":[44,68,87,152],"capture":[45],"mid-level":[46],"similarities":[47],"differences":[49],"in":[50,111,115,122,183],"image":[51,76],"layout,":[52],"object":[53],"pose,":[54],"semantic":[56,70],"content.":[57],"Contrastive":[58],"learning-based":[59,63],"CLIP":[60],"self-supervised":[62],"DINO":[64],"are":[65],"often":[66],"used":[67],"measure":[69],"similarity,":[71,136],"they":[73],"highly":[74],"compress":[75],"features,":[77],"inadequately":[78],"assessing":[79],"appearance":[80,133],"details.":[81],"This":[82],"paper":[83],"is":[84],"first":[86],"discover":[88],"that":[89,170],"pretrained":[90],"diffusion":[91],"can":[93],"be":[94],"utilized":[95],"for":[96,179],"measuring":[97,180],"visual":[98,142,154,181],"introduces":[101],"DiffSim":[103,130,171],"method,":[104],"addressing":[105],"limitations":[107],"capturing":[112],"consistency":[114],"custom":[116],"generation":[117],"tasks.":[118],"By":[119],"aligning":[120],"features":[121],"attention":[124],"layers":[125],"denoising":[128],"U-Net,":[129],"evaluates":[131],"both":[132],"style":[135,160],"showing":[137],"superior":[138],"alignment":[139],"with":[140],"human":[141],"preferences.":[143],"Additionally,":[144],"we":[145],"introduce":[146],"Sref":[148],"IP":[150],"benchmarks":[151,168],"evaluate":[153],"level":[158],"instance,":[162],"respectively.":[163],"Comprehensive":[164],"evaluations":[165],"across":[166],"multiple":[167],"demonstrate":[169],"achieves":[172],"state-of-the-art":[173],"performance,":[174],"providing":[175],"a":[176],"robust":[177],"tool":[178],"coherence":[182],"models.":[185]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}