{"id":"https://openalex.org/W4417124930","doi":"https://doi.org/10.1145/3757377.3763873","title":"Learning to Refocus with Video Diffusion Models","display_name":"Learning to Refocus with Video Diffusion Models","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417124930","doi":"https://doi.org/10.1145/3757377.3763873"},"language":null,"primary_location":{"id":"doi:10.1145/3757377.3763873","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763873","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3757377.3763873","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040466576","display_name":"SaiKiran Tedla","orcid":"https://orcid.org/0000-0002-2679-2881"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"SaiKiran Tedla","raw_affiliation_strings":["Adobe, San Jose, USA and York University, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Adobe, San Jose, USA and York University, Toronto, Canada","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066625739","display_name":"Zhoutong Zhang","orcid":"https://orcid.org/0000-0002-8144-1611"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhoutong Zhang","raw_affiliation_strings":["Adobe, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"Adobe, San Jose, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089383771","display_name":"Xuaner Zhang","orcid":"https://orcid.org/0000-0002-7679-800X"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuaner Zhang","raw_affiliation_strings":["Adobe, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"Adobe, San Jose, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070666773","display_name":"Shumian Xin","orcid":"https://orcid.org/0009-0008-3974-2876"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shumian Xin","raw_affiliation_strings":["Adobe, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"Adobe, San Jose, USA","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040466576"],"corresponding_institution_ids":["https://openalex.org/I1306409833"],"apc_list":null,"apc_paid":null,"fwci":1.1372,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85964309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9320999979972839,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9320999979972839,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.014100000262260437,"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/T11019","display_name":"Image Enhancement Techniques","score":0.00989999994635582,"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/robustness","display_name":"Robustness (evolution)","score":0.6337000131607056},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6312999725341797},{"id":"https://openalex.org/keywords/autofocus","display_name":"Autofocus","score":0.5572999715805054},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3944999873638153},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.31049999594688416},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.28700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739999890327454},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6337000131607056},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6312999725341797},{"id":"https://openalex.org/C103764139","wikidata":"https://www.wikidata.org/wiki/Q210008","display_name":"Autofocus","level":3,"score":0.5572999715805054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40149998664855957},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34689998626708984},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28029999136924744},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26820001006126404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3757377.3763873","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763873","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.19823","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.19823","pdf_url":"https://arxiv.org/pdf/2512.19823","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"}],"best_oa_location":{"id":"doi:10.1145/3757377.3763873","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757377.3763873","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1992810900","https://openalex.org/W2794775595","https://openalex.org/W2896006112","https://openalex.org/W3034582814","https://openalex.org/W3034960835","https://openalex.org/W3109494165","https://openalex.org/W3174970555","https://openalex.org/W3175200587","https://openalex.org/W3203100337","https://openalex.org/W4211065609","https://openalex.org/W4225672218","https://openalex.org/W4312497550","https://openalex.org/W4312812783","https://openalex.org/W4312933868","https://openalex.org/W4312938066","https://openalex.org/W4313177683","https://openalex.org/W4385804996","https://openalex.org/W4385815603","https://openalex.org/W4386057725","https://openalex.org/W4386071458","https://openalex.org/W4386075993","https://openalex.org/W4386076215","https://openalex.org/W4390872982","https://openalex.org/W4393149921","https://openalex.org/W4396823824","https://openalex.org/W4400580620","https://openalex.org/W4402727587","https://openalex.org/W4402775387","https://openalex.org/W4403791596","https://openalex.org/W4404966328","https://openalex.org/W4408354195","https://openalex.org/W4409369971","https://openalex.org/W4413146565"],"related_works":[],"abstract_inverted_index":{"Focus":[0],"is":[1],"a":[2,27,39,46,53,61,68],"cornerstone":[3],"of":[4,63],"photography,":[5],"yet":[6],"autofocus":[7],"systems":[8],"often":[9],"fail":[10],"to":[11,20,79],"capture":[12],"the":[13,102],"intended":[14],"subject,":[15],"and":[16,59,83,96,113],"users":[17],"frequently":[18],"wish":[19],"adjust":[21],"focus":[22],"after":[23],"capture.":[24],"We":[25,66],"introduce":[26],"novel":[28],"method":[29,87],"for":[30,104],"realistic":[31],"post-capture":[32],"refocusing":[33,58],"using":[34],"video":[35,54],"diffusion":[36],"models.":[37],"From":[38],"single":[40],"defocused":[41],"image,":[42],"our":[43],"approach":[44],"generates":[45],"perceptually":[47],"accurate":[48],"focal":[49,70],"stack,":[50],"represented":[51],"as":[52],"sequence,":[55],"enabling":[56],"interactive":[57],"unlocking":[60],"range":[62],"downstream":[64],"applications.":[65],"release":[67],"large-scale":[69],"stack":[71],"dataset":[72],"acquired":[73],"under":[74],"diverse":[75],"real-world":[76],"smartphone":[77],"conditions":[78],"support":[80],"this":[81],"work":[82],"future":[84],"research.":[85],"Our":[86],"consistently":[88],"outperforms":[89],"existing":[90],"approaches":[91],"in":[92,109],"both":[93],"perceptual":[94],"quality":[95],"robustness":[97],"across":[98],"challenging":[99],"scenarios,":[100],"paving":[101],"way":[103],"more":[105],"advanced":[106],"focus-editing":[107],"capabilities":[108],"everyday":[110],"photography.":[111],"Code":[112],"data":[114],"are":[115],"available":[116],"at":[117],"www.learn2refocus.github.io":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-08T00:00:00"}