{"id":"https://openalex.org/W7162432129","doi":"https://doi.org/10.48550/arxiv.2605.25975","title":"F-RNG: Feed-Forward Relightable Neural Gaussians","display_name":"F-RNG: Feed-Forward Relightable Neural Gaussians","publication_year":2026,"publication_date":"2026-05-25","ids":{"openalex":"https://openalex.org/W7162432129","doi":"https://doi.org/10.48550/arxiv.2605.25975"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.25975","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25975","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.25975","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136991983","display_name":"Guangming Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Guangming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053375537","display_name":"Jiahui Fan","orcid":"https://orcid.org/0000-0003-0871-7615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Jiahui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137015609","display_name":"Jian Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137048398","display_name":"Milo\u0161 Ha\u0161an","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ha\u0161an, Milo\u0161","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137010158","display_name":"Beibei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Beibei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.4341999888420105,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.4341999888420105,"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":0.18310000002384186,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1581999957561493,"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/overfitting","display_name":"Overfitting","score":0.65829998254776},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5221999883651733},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5037000179290771},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4580000042915344},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.40709999203681946},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.38530001044273376},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.38040000200271606},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.36890000104904175},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36390000581741333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8307999968528748},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.65829998254776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6208000183105469},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5221999883651733},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5037000179290771},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.36149999499320984},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.35899999737739563},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.33880001306533813},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C104317376","wikidata":"https://www.wikidata.org/wiki/Q1894545","display_name":"Gaussian blur","level":5,"score":0.2529999911785126},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.25975","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25975","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":"doi:10.48550/arxiv.2605.25975","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25975","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.42697373032569885}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Capturing":[0],"relightable":[1,83,109,130,162,167],"3D":[2,18],"assets":[3,60,85,110],"from":[4,53,86,93,136,198],"real-world":[5],"objects":[6],"is":[7,104],"a":[8,77,91,112,146,160,175],"widely":[9],"researched":[10],"problem.":[11],"Several":[12],"per-scene":[13,43],"optimization-based":[14],"methods,":[15,45],"based":[16],"on":[17],"Gaussian":[19],"splatting":[20],"(3DGS),":[21],"support":[22],"relighting;":[23],"however,":[24],"they":[25],"usually":[26],"require":[27,96],"dense":[28],"input":[29,55],"views,":[30],"and":[31,64,99,102,181,201,217],"their":[32],"overfitting":[33],"nature":[34],"makes":[35],"it":[36,103],"difficult":[37],"to":[38,107,128,151,165,234],"generalize":[39],"across":[40],"scenes.":[41],"Unlike":[42],"optimization":[44],"generalized":[46],"feed-forward":[47,78,113],"models":[48,227],"can":[49,95,195,211],"directly":[50,81],"reconstruct":[51],"Gaussians":[52],"sparse":[54],"views.":[56],"However,":[57],"the":[58,153,191,204,222,235],"resulting":[59],"have":[61],"baked-in":[62],"illumination":[63],"cannot":[65],"be":[66,212],"easily":[67],"used":[68],"for":[69],"relighting.":[70,183],"In":[71],"this":[72],"paper,":[73],"we":[74,143,158],"present":[75],"F-RNG,":[76],"framework":[79],"that":[80,210],"generates":[82],"3DGS":[84],"sparse-view":[87],"inputs.":[88],"Training":[89],"such":[90],"model":[92,126,140],"scratch":[94],"massive":[97],"data":[98,216],"computing":[100],"resources,":[101,219],"especially":[105],"challenging":[106],"generate":[108],"in":[111,203],"manner":[114],"with":[115,214],"acceptable":[116],"cost.":[117],"We":[118],"develop":[119],"F-RNG":[120,184,220,240],"upon":[121],"an":[122,137],"existing":[123],"large":[124,226],"reconstruction":[125],"(LRM)":[127],"extract":[129,166],"representations,":[131],"while":[132],"also":[133],"utilizing":[134],"priors":[135],"intrinsic":[138],"decomposition":[139],"(IDM).":[141],"Specifically,":[142],"first":[144],"introduce":[145],"latent-interpolated":[147],"fine-grained":[148],"geometry":[149,155],"synthesis":[150],"enhance":[152],"LRM's":[154],"representation.":[156],"Second,":[157],"propose":[159],"prior-guided":[161],"appearance":[163],"distillation":[164],"neural":[168,177],"representations":[169],"by":[170],"incorporating":[171],"IDM":[172],"priors.":[173],"Finally,":[174],"universal":[176],"renderer":[178],"enables":[179],"flexible":[180],"high-fidelity":[182],"requires":[185],"neither":[186],"re-training":[187],"nor":[188],"fine-tuning":[189],"of":[190,225],"underlying":[192],"LRMs,":[193],"thus":[194],"automatically":[196],"benefit":[197],"better":[199],"LRMs":[200],"IDMs":[202],"future.":[205],"With":[206],"only":[207],"small":[208],"networks":[209],"trained":[213],"affordable":[215],"computational":[218],"avoids":[221],"repetitive":[223],"inference":[224],"under":[228],"different":[229],"light":[230],"conditions.":[231],"By":[232],"comparison":[233],"state-of-the-art":[236],"LRM-based":[237],"relighting":[238],"method,":[239],"achieves":[241],"~25x":[242],"faster":[243],"relighting,":[244],"as":[245,247],"well":[246],"superior":[248],"quality":[249],"(~+2.0":[250],"dB).":[251]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-27T00:00:00"}