{"id":"https://openalex.org/W4417231734","doi":"https://doi.org/10.48550/arxiv.2504.01008","title":"IntrinsiX: High-Quality PBR Generation using Image Priors","display_name":"IntrinsiX: High-Quality PBR Generation using Image Priors","publication_year":2025,"publication_date":"2025-04-01","ids":{"openalex":"https://openalex.org/W4417231734","doi":"https://doi.org/10.48550/arxiv.2504.01008"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.01008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.01008","pdf_url":"https://arxiv.org/pdf/2504.01008","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.01008","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091037948","display_name":"Peter Kocsis","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Kocsis, Peter","raw_affiliation_strings":["Technical University of Munich"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089386176","display_name":"Lukas H\u00f6llein","orcid":"https://orcid.org/0000-0001-9494-0797"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"H\u00f6llein, Lukas","raw_affiliation_strings":["Technical University of Munich"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088583491","display_name":"Matthias Nie\u00dfner","orcid":"https://orcid.org/0000-0001-6093-5199"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nie\u00dfner, Matthias","raw_affiliation_strings":["Technical University of Munich"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091037948"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"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":null,"last_page":null},"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":0.8598999977111816,"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":0.8598999977111816,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03689999878406525,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.027699999511241913,"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":0.779699981212616},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5598000288009644},{"id":"https://openalex.org/keywords/texture-synthesis","display_name":"Texture synthesis","score":0.45239999890327454},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4471000134944916},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4074000120162964},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.3856000006198883},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.38089999556541443},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3603000044822693}],"concepts":[{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.779699981212616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124000191688538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6420000195503235},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5598000288009644},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5594000220298767},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.45239999890327454},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.3237999975681305},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2662000060081482}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2504.01008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.01008","pdf_url":"https://arxiv.org/pdf/2504.01008","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"},{"id":"doi:10.48550/arxiv.2504.01008","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.01008","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.01008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.01008","pdf_url":"https://arxiv.org/pdf/2504.01008","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,81],"introduce":[1],"IntrinsiX,":[2],"a":[3,87,99,126,169,175],"novel":[4],"method":[5],"that":[6,49,92,157],"generates":[7],"high-quality":[8],"intrinsic":[9,122,151,160],"images":[10,167],"from":[11],"text":[12],"description.":[13],"In":[14,57],"contrast":[15],"to":[16,38,59,105,113,133],"existing":[17,159],"text-to-image":[18],"models":[19,71,85],"whose":[20],"outputs":[21,37],"contain":[22],"baked-in":[23],"scene":[24],"lighting,":[25],"our":[26,61],"approach":[27],"predicts":[28],"physically-based":[29],"rendering":[30,127],"(PBR)":[31],"maps.":[32],"This":[33,102],"enables":[34],"the":[35,135,143],"generated":[36,166],"be":[39],"used":[40,164],"for":[41,72],"content":[42],"creation":[43],"scenarios":[44],"in":[45,98,142],"core":[46],"graphics":[47],"applications":[48],"facilitate":[50],"re-lighting,":[51,180],"editing,":[52,181],"and":[53,68,95,112,182],"texture":[54,186],"generation":[55,152],"tasks.":[56],"order":[58],"train":[60],"generator,":[62],"we":[63,124,173],"exploit":[64],"strong":[65,154],"image":[66,161],"priors,":[67],"pre-train":[69],"separate":[70],"each":[73,109,121],"PBR":[74,117,185],"material":[75],"component":[76],"(albedo,":[77],"roughness,":[78],"metallic,":[79],"normals).":[80],"then":[82],"align":[83],"these":[84],"with":[86,153,165],"new":[88],"cross-intrinsic":[89],"attention":[90],"formulation":[91],"concatenates":[93],"key":[94],"value":[96],"features":[97],"consistent":[100],"fashion.":[101],"allows":[103],"us":[104],"exchange":[106],"information":[107],"between":[108],"output":[110,144],"modality":[111],"obtain":[114],"semantically":[115],"coherent":[116],"predictions.":[118],"To":[119],"ground":[120],"component,":[123],"propose":[125],"loss":[128],"which":[129],"provides":[130],"image-space":[131],"signals":[132],"constrain":[134],"model,":[136],"thus":[137],"facilitating":[138],"sharp":[139],"details":[140],"also":[141],"BRDF":[145],"properties.":[146],"Our":[147],"results":[148],"demonstrate":[149],"detailed":[150],"generalization":[155],"capabilities":[156],"outperforms":[158],"decomposition":[162],"methods":[163],"by":[168],"significant":[170],"margin.":[171],"Finally,":[172],"show":[174],"series":[176],"of":[177],"applications,":[178],"including":[179],"text-conditioned":[183],"room-scale":[184],"generation.":[187]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}