{"id":"https://openalex.org/W7168464665","doi":"https://doi.org/10.1145/3799902.3811065","title":"VeraRetouch: A Lightweight Fully Differentiable Framework for Multi-Task Reasoning Photo Retouching","display_name":"VeraRetouch: A Lightweight Fully Differentiable Framework for Multi-Task Reasoning Photo Retouching","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7168464665","doi":"https://doi.org/10.1145/3799902.3811065"},"language":null,"primary_location":{"id":"doi:10.1145/3799902.3811065","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811065","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799902.3811065","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100954302","display_name":"Guo Yihong","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihong Guo","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-8919-7984","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069781278","display_name":"Youwei Lyu","orcid":"https://orcid.org/0000-0002-6723-3517"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youwei Lyu","raw_affiliation_strings":["vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6723-3517","affiliations":[{"raw_affiliation_string":"vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., Shanghai, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008802390","display_name":"Jiajun Tang","orcid":"https://orcid.org/0000-0002-0254-9764"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Tang","raw_affiliation_strings":["vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0254-9764","affiliations":[{"raw_affiliation_string":"vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058976282","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0002-4177-8818"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhuo Zhou","raw_affiliation_strings":["Zhejiang University, Hanghzou, China"],"raw_orcid":"https://orcid.org/0009-0006-1334-8235","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hanghzou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140995155","display_name":"Hongliang Wang","orcid":"https://orcid.org/0009-0008-2977-2852"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongliang Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-2977-2852","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Hangzhou, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141046296","display_name":"Jinwei Chen","orcid":"https://orcid.org/0009-0002-8954-0873"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinwei Chen","raw_affiliation_strings":["vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-8954-0873","affiliations":[{"raw_affiliation_string":"vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604564","display_name":"Changqing Zou","orcid":"https://orcid.org/0000-0001-8264-6849"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changqing Zou","raw_affiliation_strings":["Zhejiang Lab, Hangzhou, China and Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8264-6849","affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, China and Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030729327","display_name":"Qingnan Fan","orcid":"https://orcid.org/0000-0003-1249-2826"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingnan Fan","raw_affiliation_strings":["vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1249-2826","affiliations":[{"raw_affiliation_string":"vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6973000168800354},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6694999933242798},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.34209999442100525},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3391000032424927},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.33799999952316284},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3278999924659729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541999816894531},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6973000168800354},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6694999933242798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5145999789237976},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2849000096321106},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2522999942302704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3799902.3811065","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811065","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3799902.3811065","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811065","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1964859077","https://openalex.org/W2302255633","https://openalex.org/W2735974062","https://openalex.org/W2798844427","https://openalex.org/W2963156339","https://openalex.org/W2963466723","https://openalex.org/W2963967766","https://openalex.org/W2998723654","https://openalex.org/W3009375329","https://openalex.org/W3035229960","https://openalex.org/W3088065502","https://openalex.org/W3089217465","https://openalex.org/W3127867299","https://openalex.org/W3134281927","https://openalex.org/W3176674719","https://openalex.org/W4214665850","https://openalex.org/W4312579682","https://openalex.org/W4382459069","https://openalex.org/W4386076169","https://openalex.org/W4386076215","https://openalex.org/W4390873485","https://openalex.org/W4403780656","https://openalex.org/W4412673702","https://openalex.org/W4413144805","https://openalex.org/W7133200339"],"related_works":[],"abstract_inverted_index":{"Reasoning":[0],"photo":[1,57],"retouching":[2,19,72],"has":[3],"gained":[4],"significant":[5],"traction,":[6],"requiring":[7],"models":[8],"to":[9,70],"analyze":[10],"image":[11],"defects,":[12],"give":[13],"reasoning":[14],"processes,":[15],"and":[16,33,39,51,77,105],"execute":[17],"precise":[18],"enhancements.":[20],"However,":[21],"existing":[22],"approaches":[23],"often":[24],"rely":[25],"on":[26,75],"non-differentiable":[27],"external":[28,90],"software,":[29],"creating":[30],"optimization":[31],"barriers":[32],"suffering":[34],"from":[35],"high":[36],"parameter":[37],"redundancy":[38],"limited":[40],"generalization.":[41],"To":[42,109],"address":[43],"these":[44],"challenges,":[45],"we":[46,81,113,131],"propose":[47,132],"VeraRetouch,":[48],"a":[49,61,83,125,134,157],"lightweight":[50],"fully":[52,84],"differentiable":[53,85],"framework":[54],"for":[55,101,120],"multi-task":[56],"retouching.":[58],"We":[59],"employ":[60],"0.5B":[62],"Vision-Language":[63],"Model":[64],"(VLM)":[65],"as":[66],"the":[67,116],"central":[68],"intelligence":[69],"formulate":[71],"plans":[73],"based":[74],"instructions":[76],"scene":[78],"semantics.":[79],"Furthermore,":[80,130],"develop":[82],"Retouch":[86],"Renderer":[87],"that":[88,139,147],"replaces":[89],"tools,":[91],"enabling":[92,161],"direct":[93],"end-to-end":[94],"pixel-level":[95],"training":[96],"through":[97],"decoupled":[98],"control":[99],"latents":[100],"lighting,":[102],"global":[103],"color,":[104],"specific":[106],"color":[107],"adjustments.":[108],"overcome":[110],"data":[111],"scarcity,":[112],"introduce":[114],"AetherRetouch-1M+,":[115],"first":[117],"million-scale":[118],"dataset":[119],"professional":[121],"retouching,":[122],"constructed":[123],"via":[124],"new":[126],"inverse":[127],"degradation":[128],"workflow.":[129],"DAPO-AE,":[133],"reinforcement":[135],"learning":[136],"post-training":[137],"strategy":[138],"enhances":[140],"autonomous":[141],"aesthetic":[142],"cognition.":[143],"Extensive":[144],"experiments":[145],"demonstrate":[146],"VeraRetouch":[148],"achieves":[149],"state-of-the-art":[150],"performance":[151],"across":[152],"multiple":[153],"benchmarks":[154],"while":[155],"maintaining":[156],"significantly":[158],"smaller":[159],"footprint,":[160],"mobile":[162],"deployment.":[163]},"counts_by_year":[],"updated_date":"2026-07-17T05:58:32.477365","created_date":"2026-07-17T00:00:00"}