{"id":"https://openalex.org/W7137875688","doi":"https://doi.org/10.1609/aaai.v40i6.42462","title":"A Geometric Perspective on Optimizing Vector Quantized Latent Diffusion Model for Image Restoration","display_name":"A Geometric Perspective on Optimizing Vector Quantized Latent Diffusion Model for Image Restoration","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137875688","doi":"https://doi.org/10.1609/aaai.v40i6.42462"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i6.42462","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42462","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i6.42462","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129752258","display_name":"Chen Hang","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Hang","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129643403","display_name":"Haoming Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoming Chen","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081732312","display_name":"Xuwei Fang","orcid":"https://orcid.org/0009-0005-7420-1600"},"institutions":[{"id":"https://openalex.org/I4210104238","display_name":"Building Engineering and Science Talent","ror":"https://ror.org/00rkxnb56","country_code":"US","type":"other","lineage":["https://openalex.org/I4210104238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuwei Fang","raw_affiliation_strings":["Bestpay AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bestpay AI Lab","institution_ids":["https://openalex.org/I4210104238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009911905","display_name":"Weisheng Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104238","display_name":"Building Engineering and Science Talent","ror":"https://ror.org/00rkxnb56","country_code":"US","type":"other","lineage":["https://openalex.org/I4210104238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weisheng Xie","raw_affiliation_strings":["Bestpay AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bestpay AI Lab","institution_ids":["https://openalex.org/I4210104238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129680773","display_name":"Xiangxiang Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104238","display_name":"Building Engineering and Science Talent","ror":"https://ror.org/00rkxnb56","country_code":"US","type":"other","lineage":["https://openalex.org/I4210104238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangxiang Gao","raw_affiliation_strings":["Bestpay AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bestpay AI Lab","institution_ids":["https://openalex.org/I4210104238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044588347","display_name":"Faming Fang","orcid":"https://orcid.org/0000-0003-4511-4813"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Faming Fang","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129643205","display_name":"Guixu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guixu Zhang","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125751769","display_name":"Haichuan Song","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haichuan Song","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":2,"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":"40","issue":"6","first_page":"4619","last_page":"4626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.48410001397132874,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.48410001397132874,"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":0.32820001244544983,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.05119999870657921,"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/vector-quantization","display_name":"Vector quantization","score":0.5812000036239624},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.5540000200271606},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4814000129699707},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.38589999079704285},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.36390000581741333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3499999940395355},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.33739998936653137}],"concepts":[{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.5540000200271606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5533999800682068},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5368000268936157},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4814000129699707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4796999990940094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3898000121116638},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32089999318122864},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C137318105","wikidata":"https://www.wikidata.org/wiki/Q36255","display_name":"Direction vector","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i6.42462","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42462","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/42462","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/42462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i6.42462","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42462","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7101483941078186,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,59,80],"paper,":[2],"we":[3,57,82,90,138],"investigate":[4],"the":[5,8,24,38,63,68,74,105,110,122,129,132],"limitations":[6],"of":[7,41,65,71,131],"Vector":[9,25],"Quantized":[10],"Latent":[11],"Diffusion":[12,29],"Model":[13,30],"(VQ-LDM)":[14],"in":[15,67],"restoration":[16,159],"tasks.":[17],"We":[18],"identify":[19],"a":[20,34,84,92,141,153],"performance":[21,106],"gap":[22,60,107],"between":[23,37],"Quantization":[26],"(VQ)":[27],"and":[28,49],"components,":[31],"manifested":[32],"as":[33],"significant":[35],"discrepancy":[36],"reconstruction":[39],"quality":[40],"ground":[42],"truth":[43],"images":[44,51],"processed":[45],"via":[46],"VQ":[47,72],"autoregression":[48],"degraded":[50],"restored":[52],"by":[53,108,118],"VQ-LDM.":[54],"Through":[55],"experiments,":[56],"attribute":[58],"primarily":[61],"to":[62,128],"lack":[64],"robustness":[66],"mapped":[69,112],"points":[70,113],"within":[73],"original":[75,111],"VQ-LDM":[76],"framework.":[77],"To":[78],"address":[79],"issue,":[81],"propose":[83,140],"geometric":[85,154],"based":[86],"optimization":[87],"approach.":[88],"First,":[89],"introduce":[91],"simple":[93],"yet":[94],"effective":[95],"method,":[96],"termed":[97],"interpolation-based":[98],"latent":[99,123,144],"initial":[100,124,145],"state":[101,125,146],"optimization,":[102,147],"which":[103],"mitigates":[104],"replacing":[109],"with":[114],"interpolated":[115],"values,":[116],"supported":[117],"theoretical":[119,150],"analysis.":[120],"Here,":[121],"refers":[126],"specifically":[127],"input":[130],"diffusion":[133],"model.":[134],"Building":[135],"upon":[136],"this,":[137],"further":[139,157],"Chebyshev":[142],"center-based":[143],"an":[148],"elegant":[149],"solution":[151],"from":[152],"perspective,":[155],"that":[156],"enhances":[158],"performance.":[160],"Our":[161],"improvements":[162],"consistently":[163],"achieve":[164],"superior":[165],"results":[166],"across":[167],"nine":[168],"benchmark":[169],"datasets.":[170]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}