{"id":"https://openalex.org/W4417282109","doi":"https://doi.org/10.1109/iccv51701.2025.01991","title":"OmniDiff: A Comprehensive Benchmark for Fine-Grained Image Difference Captioning","display_name":"OmniDiff: A Comprehensive Benchmark for Fine-Grained Image Difference Captioning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417282109","doi":"https://doi.org/10.1109/iccv51701.2025.01991"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01991","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/2503.11093","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100390946","display_name":"Yuan Liu","orcid":"https://orcid.org/0000-0003-3892-480X"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Liu","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008135133","display_name":"Saihui Hou","orcid":"https://orcid.org/0000-0003-4689-2860"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Saihui Hou","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University","School of Artificial Intelligence, Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Saijie Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Saijie Hou","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University","School of Artificial Intelligence, Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118145755","display_name":"Jiabao Du","orcid":null},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabao Du","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004250903","display_name":"Shibei Meng","orcid":"https://orcid.org/0009-0007-1078-6317"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shibei Meng","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086866868","display_name":"Yong\u2010Zhen Huang","orcid":"https://orcid.org/0000-0002-0529-4947"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongzhen Huang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"21440","last_page":"21449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9934999942779541,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9934999942779541,"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":0.0010000000474974513,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0006000000284984708,"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/closed-captioning","display_name":"Closed captioning","score":0.9182000160217285},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6168000102043152},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.61080002784729},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5349000096321106},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5149999856948853},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45840001106262207},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.439300000667572}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9182000160217285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857000231742859},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6168000102043152},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.61080002784729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5958999991416931},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5349000096321106},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38960000872612},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.358599990606308},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3476000130176544},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.26100000739097595}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.01991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01991","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:2503.11093","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11093","pdf_url":"https://arxiv.org/pdf/2503.11093","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2503.11093","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2503.11093","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.11093","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:2503.11093","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11093","pdf_url":"https://arxiv.org/pdf/2503.11093","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4351044990","display_name":null,"funder_award_id":"62206022,62276025,62476027","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7833981074","display_name":null,"funder_award_id":"2253200026","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"Difference":[1],"Captioning":[2],"(IDC)":[3],"aims":[4],"to":[5,53,136,180,193],"generate":[6],"natural":[7],"language":[8,119],"descriptions":[9],"of":[10,56,153],"subtle":[11],"differences":[12,142],"between":[13],"image":[14],"pairs,":[15],"requiring":[16],"both":[17],"precise":[18],"visual":[19],"change":[20,107],"localization":[21],"and":[22,34,41,61,91,103,139,169,186],"coherent":[23],"semantic":[24],"expression.":[25],"Despite":[26],"recent":[27],"advancements,":[28],"existing":[29,181],"datasets":[30,50],"often":[31,69],"lack":[32],"breadth":[33,47],"depth,":[35],"limiting":[36],"their":[37],"applicability":[38],"in":[39,58,101,174],"complex":[40,89],"dynamic":[42],"environments:":[43],"(1)":[44],"from":[45,63],"a":[46,64,81,116,123],"perspective,":[48,66],"current":[49],"are":[51],"constrained":[52],"limited":[54],"variations":[55],"objects":[57],"specific":[59],"scenes,":[60],"(2)":[62],"depth":[65],"prior":[67],"benchmarks":[68],"provide":[70],"overly":[71],"simplistic":[72],"descriptions.":[73],"To":[74],"address":[75],"these":[76],"challenges,":[77],"we":[78,113],"introduce":[79],"OmniDiff,":[80,170],"comprehensive":[82],"dataset":[83],"comprising":[84],"324":[85],"diverse":[86],"scenarios-spanning":[87],"real-world":[88],"environments":[90],"3D":[92],"synthetic":[93],"settings-with":[94],"fine-grained":[95],"human":[96],"annotations":[97],"averaging":[98],"60":[99],"words":[100],"length":[102],"covering":[104],"12":[105],"distinct":[106],"types.":[108],"Building":[109],"on":[110],"this":[111],"foundation,":[112],"propose":[114],"M$^3$Diff,":[115],"MultiModal":[117],"large":[118],"model":[120],"enhanced":[121],"by":[122],"plug-and-play":[124],"Multi-scale":[125],"Differential":[126],"Perception":[127],"(MDP)":[128],"module.":[129],"This":[130],"module":[131],"improves":[132],"the":[133,145,151,154],"model's":[134,147],"ability":[135],"accurately":[137],"identify":[138],"describe":[140],"inter-image":[141],"while":[143],"maintaining":[144],"foundational":[146],"generalization":[148],"capabilities.":[149],"With":[150],"addition":[152],"OmniDiff":[155],"dataset,":[156,184],"M$^3$Diff":[157],"achieves":[158],"state-of-the-art":[159],"performance":[160],"across":[161],"multiple":[162],"benchmarks,":[163],"including":[164],"Spot-the-Diff,":[165],"IEdit,":[166],"CLEVR-Change,":[167],"CLEVR-DC,":[168],"demonstrating":[171],"significant":[172],"improvements":[173],"cross-scenario":[175],"difference":[176],"recognition":[177],"accuracy":[178],"compared":[179],"methods.":[182],"The":[183],"code,":[185],"models":[187],"will":[188],"be":[189],"made":[190],"publicly":[191],"available":[192],"support":[194],"further":[195],"research.":[196]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}