{"id":"https://openalex.org/W4415708254","doi":"https://doi.org/10.1109/icme59968.2025.11210202","title":"DreamPBR: Text-driven High-Resolution SVBRDF Generation with Multimodal Guidance","display_name":"DreamPBR: Text-driven High-Resolution SVBRDF Generation with Multimodal Guidance","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708254","doi":"https://doi.org/10.1109/icme59968.2025.11210202"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104287345","display_name":"Linxuan Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linxuan Xin","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459097","display_name":"Zheng Zhang","orcid":"https://orcid.org/0000-0002-1398-7727"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]},{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd.,China","institution_ids":["https://openalex.org/I2250955327","https://openalex.org/I4210144487","https://openalex.org/I4210146936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101150614","display_name":"Zhiyi Pan","orcid":"https://orcid.org/0009-0008-2050-3947"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyi Pan","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112961541","display_name":"Jinfu Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfu Wei","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064472970","display_name":"Duan Gao","orcid":"https://orcid.org/0000-0002-0647-6160"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]},{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Duan Gao","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd.,China","institution_ids":["https://openalex.org/I2250955327","https://openalex.org/I4210144487","https://openalex.org/I4210146936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079733529","display_name":"Wei Gao","orcid":"https://orcid.org/0000-0001-9336-2729"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Gao","raw_affiliation_strings":["Peking University,School of Electronic and Computer Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Electronic and Computer Engineering,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2409,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95175907,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.5687000155448914,"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":0.5687000155448914,"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":0.22380000352859497,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.09210000187158585,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/rendering","display_name":"Rendering (computer graphics)","score":0.6432999968528748},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.6136000156402588},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5432999730110168},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5397999882698059},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.361299991607666},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.34279999136924744},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.33820000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984000205993652},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6432999968528748},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.6136000156402588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5514000058174133},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5397999882698059},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4618000090122223},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.361299991607666},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C2778045648","wikidata":"https://www.wikidata.org/wiki/Q176827","display_name":"Markov random field","level":4,"score":0.2987000048160553},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.2694999873638153},{"id":"https://openalex.org/C108597893","wikidata":"https://www.wikidata.org/wiki/Q663650","display_name":"Reflectivity","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2736596523","https://openalex.org/W2811490555","https://openalex.org/W2958302123","https://openalex.org/W2962785568","https://openalex.org/W2963650738","https://openalex.org/W2965557046","https://openalex.org/W2983859346","https://openalex.org/W3090135481","https://openalex.org/W3096831136","https://openalex.org/W3106672182","https://openalex.org/W3109203742","https://openalex.org/W3183743915","https://openalex.org/W3204971388","https://openalex.org/W4205486372","https://openalex.org/W4205633319","https://openalex.org/W4214774769","https://openalex.org/W4280629715","https://openalex.org/W4282917439","https://openalex.org/W4283825676","https://openalex.org/W4285981709","https://openalex.org/W4312933868","https://openalex.org/W4367180575","https://openalex.org/W4367189632","https://openalex.org/W4389539690","https://openalex.org/W4390873054","https://openalex.org/W4401917881"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"material":[1,51,65,70,124],"creation":[2],"methods":[3],"are":[4],"limited":[5],"in":[6,123],"diversity":[7],"due":[8],"to":[9,75,79],"the":[10],"scarcity":[11],"of":[12,47,55],"real-world":[13],"data.":[14],"To":[15,102],"enhance":[16],"controllability":[17],"and":[18,36,115,129,135],"diversity,":[19],"we":[20,61,106],"propose":[21],"DreamPBR,":[22],"a":[23,69,98,108],"diffusion-based":[24],"generative":[25],"framework":[26],"that":[27,112],"creates":[28],"spatially":[29],"varying":[30],"appearance":[31],"properties":[32],"guided":[33],"by":[34],"text":[35],"multimodal":[37,109],"controls.":[38],"By":[39],"integrating":[40],"large-scale":[41],"vision-language":[42],"models":[43],"trained":[44],"on":[45],"billions":[46],"text-image":[48],"pairs":[49],"with":[50],"priors":[52],"from":[53],"hundreds":[54],"Physically":[56],"Based":[57],"Rendering":[58],"(PBR)":[59],"samples,":[60],"achieve":[62,103],"high-quality":[63],"PBR":[64,100],"generation.":[66],"We":[67,119],"employ":[68],"Latent":[71],"Diffusion":[72],"Model":[73],"(m-LDM)":[74],"map":[76],"albedo":[77],"maps":[78,96],"latent":[80],"space,":[81],"which":[82],"is":[83],"then":[84],"decoded":[85],"into":[86],"full":[87],"Spatially":[88],"Varying":[89],"Bidirectional":[90],"Reflectance":[91],"Distribution":[92],"Function":[93],"(SVBRDF)":[94],"parameter":[95],"via":[97],"rendering-aware":[99],"decoder.":[101],"diverse":[104],"control,":[105],"introduce":[107],"guidance":[110],"module":[111],"includes":[113],"image":[114],"3D":[116],"shape":[117],"guidance.":[118],"demonstrate":[120],"DreamPBR\u2019s":[121],"effectiveness":[122],"creation,":[125],"showcasing":[126],"its":[127],"versatility":[128],"user-friendliness":[130],"across":[131],"various":[132],"controllable":[133],"generation":[134],"editing":[136],"applications.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}
