{"id":"https://openalex.org/W4416610178","doi":"https://doi.org/10.1109/iccv51701.2025.01723","title":"HiGarment: Cross-Modal Harmony Based Diffusion Model for Flat Sketch to Realistic Garment Image","display_name":"HiGarment: Cross-Modal Harmony Based Diffusion Model for Flat Sketch to Realistic Garment Image","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416610178","doi":"https://doi.org/10.1109/iccv51701.2025.01723"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01723","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/2505.23186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100681086","display_name":"Jun-Yi Guo","orcid":"https://orcid.org/0000-0002-5186-8067"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyi Guo","raw_affiliation_strings":["Xi&#x0027;an Jiaotong Liverpool University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an Jiaotong Liverpool University","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100688790","display_name":"Jingxuan Zhang","orcid":"https://orcid.org/0000-0002-1655-6121"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingxuan Zhang","raw_affiliation_strings":["Xi&#x0027;an Jiaotong Liverpool University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an Jiaotong Liverpool University","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026986847","display_name":"Fangyu Wu","orcid":"https://orcid.org/0000-0001-9618-8965"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyu Wu","raw_affiliation_strings":["Xi&#x0027;an Jiaotong Liverpool University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an Jiaotong Liverpool University","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047918772","display_name":"Huanda Lu","orcid":"https://orcid.org/0000-0002-4924-1038"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huanda Lu","raw_affiliation_strings":["NingboTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NingboTech University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053452551","display_name":"Qiufeng Wang","orcid":"https://orcid.org/0000-0002-0918-4606"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiufeng Wang","raw_affiliation_strings":["Xi&#x0027;an Jiaotong Liverpool University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an Jiaotong Liverpool University","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019284302","display_name":"Wenmian Yang","orcid":"https://orcid.org/0000-0001-8493-4449"},"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":"Wenmian Yang","raw_affiliation_strings":["Beijing Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033755146","display_name":"Eng Gee Lim","orcid":"https://orcid.org/0000-0003-0199-7386"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Eng Gee Lim","raw_affiliation_strings":["Xi&#x0027;an Jiaotong Liverpool University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an Jiaotong Liverpool University","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103026893","display_name":"Dongming Lu","orcid":"https://orcid.org/0000-0001-7559-477X"},"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":"Dongming Lu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18542","last_page":"18551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.968500018119812,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.968500018119812,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.011300000362098217,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11448","display_name":"Face recognition and analysis","score":0.00559999980032444,"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/sketch","display_name":"Sketch","score":0.8655999898910522},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5281999707221985},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.521399974822998},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48730000853538513},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4564000070095062},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3828999996185303},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.32659998536109924},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.32600000500679016}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.8655999898910522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.71670001745224},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5281999707221985},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4934000074863434},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48840001225471497},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.47130000591278076},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.353300005197525},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25450000166893005},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01723","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:2505.23186","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23186","pdf_url":"https://arxiv.org/pdf/2505.23186","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":"doi:10.48550/arxiv.2505.23186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.23186","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:2505.23186","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23186","pdf_url":"https://arxiv.org/pdf/2505.23186","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/G7861488906","display_name":null,"funder_award_id":"62436009,62276258","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416610178.pdf","grobid_xml":"https://content.openalex.org/works/W4416610178.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion-based":[0],"garment":[1,16,41,98,173,186],"synthesis":[2,152],"tasks":[3],"primarily":[4],"focus":[5],"on":[6],"the":[7,11,15,91,168,181],"design":[8],"phase":[9],"in":[10,185],"fashion":[12],"domain,":[13],"while":[14,100],"production":[17],"process":[18],"remains":[19],"largely":[20],"underexplored.":[21],"To":[22,104],"bridge":[23],"this":[24,106],"gap,":[25],"we":[26,108,163],"introduce":[27],"a":[28,111,120,136],"new":[29],"task:":[30],"Flat":[31],"Sketch":[32],"to":[33,75,93],"Realistic":[34],"Garment":[35],"Image":[36],"(FS2RG),":[37],"which":[38,71],"generates":[39],"realistic":[40],"images":[42],"by":[43,61,153],"integrating":[44],"flat":[45,81,145],"sketches":[46,82,146],"and":[47,83,131,134,147,177,190],"textual":[48,62,84,130],"guidance.":[49],"FS2RG":[50],"presents":[51],"two":[52,116],"key":[53],"challenges:":[54],"1)":[55],"fabric":[56,78,127],"characteristics":[57],"are":[58,192],"solely":[59],"guided":[60],"prompts,":[63,149],"providing":[64],"insufficient":[65],"visual":[66,132],"supervision":[67],"for":[68,172],"diffusion-based":[69],"models,":[70],"limits":[72],"their":[73],"ability":[74],"capture":[76],"fine-grained":[77],"details;":[79],"2)":[80],"guidance":[85],"may":[86],"provide":[87],"conflicting":[88],"information,":[89],"requiring":[90],"model":[92],"selectively":[94],"preserve":[95],"or":[96,158],"modify":[97],"attributes":[99],"maintaining":[101],"structural":[102],"coherence.":[103],"tackle":[105],"task,":[107],"propose":[109],"HiGarment,":[110],"novel":[112],"framework":[113],"that":[114,125,140],"comprises":[115],"core":[117],"components:":[118],"i)":[119],"multi-modal":[121],"semantic":[122],"enhancement":[123],"mechanism":[124,139],"enhances":[126],"representation":[128],"across":[129],"modalities,":[133],"ii)":[135],"harmonized":[137],"cross-attention":[138],"dynamically":[141],"balances":[142],"information":[143],"from":[144],"text":[148],"allowing":[150],"controllable":[151],"generating":[154],"either":[155],"sketch-aligned":[156],"(image-biased)":[157],"text-guided":[159],"(text-biased)":[160],"outputs.":[161],"Furthermore,":[162],"collect":[164],"Multi-modal":[165],"Detailed":[166],"Garment,":[167],"largest":[169],"open-source":[170],"dataset":[171,191],"generation.":[174],"Experimental":[175],"results":[176],"user":[178],"studies":[179],"demonstrate":[180],"effectiveness":[182],"of":[183],"HiGarment":[184],"synthesis.":[187],"The":[188],"code":[189],"available":[193],"at":[194],"https://github.com/Maple498/HiGarment.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
