{"id":"https://openalex.org/W7166748168","doi":"https://doi.org/10.48550/arxiv.2606.30380","title":"RenderFormer++: Scalable and Physically Grounded Feed-Forward Neural Rendering","display_name":"RenderFormer++: Scalable and Physically Grounded Feed-Forward Neural Rendering","publication_year":2026,"publication_date":"2026-06-29","ids":{"openalex":"https://openalex.org/W7166748168","doi":"https://doi.org/10.48550/arxiv.2606.30380"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.30380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30380","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.2606.30380","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012679784","display_name":"Haijun Du","orcid":"https://orcid.org/0000-0001-5425-5488"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Huangsheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058268359","display_name":"Hao Zhu","orcid":"https://orcid.org/0000-0003-4411-0933"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139671793","display_name":"Youcheng Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Youcheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130592596","display_name":"Jinyang Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Jinyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139689292","display_name":"Ligang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ligang","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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.8833000063896179,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.8833000063896179,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.07739999890327454,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.016599999740719795,"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/rendering","display_name":"Rendering (computer graphics)","score":0.829800009727478},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6765999794006348},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43209999799728394},{"id":"https://openalex.org/keywords/global-illumination","display_name":"Global illumination","score":0.41040000319480896},{"id":"https://openalex.org/keywords/texture-memory","display_name":"Texture memory","score":0.3986999988555908},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.37439998984336853}],"concepts":[{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.829800009727478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072999715805054},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6765999794006348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4970000088214874},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C89720835","wikidata":"https://www.wikidata.org/wiki/Q1531701","display_name":"Global illumination","level":3,"score":0.41040000319480896},{"id":"https://openalex.org/C18766215","wikidata":"https://www.wikidata.org/wiki/Q7708532","display_name":"Texture memory","level":5,"score":0.3986999988555908},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.37439998984336853},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C73313986","wikidata":"https://www.wikidata.org/wiki/Q355386","display_name":"Luminance","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C110541219","wikidata":"https://www.wikidata.org/wiki/Q72948","display_name":"Path tracing","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C36816356","wikidata":"https://www.wikidata.org/wiki/Q16911860","display_name":"3D rendering","level":3,"score":0.30239999294281006},{"id":"https://openalex.org/C44185422","wikidata":"https://www.wikidata.org/wiki/Q6002064","display_name":"Image-based modeling and rendering","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.26759999990463257}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.30380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30380","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.2606.30380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30380","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,78],"present":[1],"RenderFormer++,":[2],"a":[3],"scalable":[4],"and":[5,36,67,101,107,118,132],"physically":[6,73],"grounded":[7],"feed-forward":[8,120],"neural":[9,20,136],"rendering":[10,21,123,137],"framework":[11],"for":[12],"global":[13,121],"illumination":[14,122],"in":[15],"mesh":[16],"scenes.":[17],"Existing":[18],"Transformer-based":[19],"methods":[22],"such":[23],"as":[24],"RenderFormer":[25],"achieve":[26],"promising":[27],"cross-scene":[28],"generalization,":[29],"but":[30],"suffer":[31],"from":[32],"limited":[33],"physical":[34,130],"consistency":[35,70],"poor":[37],"scalability":[38],"due":[39],"to":[40],"the":[41,64],"quadratic":[42],"attention":[43,65],"complexity":[44],"of":[45],"triangle-level":[46,87],"tokenization.":[47],"To":[48],"address":[49],"these":[50],"issues,":[51],"we":[52],"introduce":[53],"Physics-Informed":[54],"Transport":[55],"Guidance":[56],"(PITG),":[57],"which":[58,85],"embeds":[59],"rendering-equation":[60],"inductive":[61],"biases":[62],"into":[63,89],"mechanism":[66],"enforces":[68],"transport":[69,76],"loss,":[71],"enabling":[72],"consistent":[74],"light":[75],"modeling.":[77],"further":[79],"propose":[80],"Hierarchical":[81],"Object-Centric":[82],"Tokenization":[83],"(HOCT),":[84],"aggregates":[86],"features":[88],"compact":[90],"object-level":[91],"tokens":[92],"via":[93],"cross-attention":[94],"with":[95,128],"learnable":[96],"queries,":[97],"substantially":[98],"reducing":[99],"computational":[100],"memory":[102],"costs":[103],"while":[104],"preserving":[105],"geometric":[106],"radiometric":[108],"information.":[109],"Extensive":[110],"experiments":[111],"demonstrate":[112],"that":[113],"RenderFormer++":[114],"achieves":[115],"scalable,":[116],"stable,":[117],"generalizable":[119],"across":[124],"complex":[125],"large-scale":[126],"scenes":[127],"improved":[129],"accuracy":[131],"efficiency":[133],"over":[134],"prior":[135],"methods.":[138]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}