{"id":"https://openalex.org/W4415318366","doi":"https://doi.org/10.52202/085713-5811","title":"Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers","display_name":"Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415318366","doi":"https://doi.org/10.52202/085713-5811"},"language":"en","primary_location":{"id":"doi:10.52202/085713-5811","doi":"https://doi.org/10.52202/085713-5811","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-5811","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W4415318366"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.07316","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051326863","display_name":"Gangwei Xu","orcid":"https://orcid.org/0009-0007-0435-4534","observed_orcids":["https://orcid.org/0009-0007-0435-4534"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangwei Xu","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011625261","display_name":"Haotong Lin","orcid":"https://orcid.org/0000-0001-5862-3268","observed_orcids":["https://orcid.org/0000-0001-5862-3268"]},"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":"Haotong Lin","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101871631","display_name":"Hongcheng Luo","orcid":"https://orcid.org/0000-0002-0058-3571","observed_orcids":["https://orcid.org/0000-0002-0058-3571"]},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongcheng Luo","raw_affiliation_strings":["Xiaomi Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071338040","display_name":"Xianqi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianqi Wang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108920046","display_name":"Jingfeng Yao","orcid":"https://orcid.org/0009-0001-7775-0542","observed_orcids":["https://orcid.org/0009-0001-7775-0542"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JINGFENG YAO","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013383175","display_name":"Lianghui Zhu","orcid":"https://orcid.org/0009-0005-3067-0210","observed_orcids":["https://orcid.org/0009-0005-3067-0210"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianghui Zhu","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061682399","display_name":"Yuechuan Pu","orcid":"https://orcid.org/0000-0002-3407-2948","observed_orcids":["https://orcid.org/0000-0002-3407-2948"]},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuechuan Pu","raw_affiliation_strings":["Horizon Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Horizon Robotics","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cheng Chi_","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]},{"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":"Cheng Chi_","raw_affiliation_strings":["Huazhong University of Science and Technology, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I47720641","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100308768","display_name":"Haiyang Sun","orcid":"https://orcid.org/0009-0005-4164-5213","observed_orcids":["https://orcid.org/0009-0005-4164-5213","https://orcid.org/0009-0004-3485-3869"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haiyang Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103090753","display_name":"Bing Wang","orcid":"https://orcid.org/0009-0007-6166-7801","observed_orcids":["https://orcid.org/0009-0007-6166-7801"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Wang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102992722","display_name":"Guang Chen","orcid":"https://orcid.org/0000-0003-1487-8044","observed_orcids":["https://orcid.org/0000-0003-1487-8044","https://orcid.org/0000-0001-7251-1596"]},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Chen","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080844671","display_name":"Hangjun Ye","orcid":"https://orcid.org/0009-0001-9570-7927","observed_orcids":["https://orcid.org/0009-0001-9570-7927"]},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangjun Ye","raw_affiliation_strings":["Xiaomi Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073087748","display_name":"Sida Peng","orcid":"https://orcid.org/0000-0001-6546-4525","observed_orcids":["https://orcid.org/0000-0001-6546-4525","https://orcid.org/0000-0002-2151-0523","https://orcid.org/0009-0001-7874-3838"]},"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":"Sida Peng","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068792201","display_name":"Xin She Yang","orcid":"https://orcid.org/0000-0002-8046-722X","observed_orcids":["https://orcid.org/0000-0002-8046-722X"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":["https://openalex.org/I4405256866"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.3318,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.98942131,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"193525","last_page":"193549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.7188000082969666,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.7188000082969666,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.13680000603199005,"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":0.07569999992847443,"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/monocular-depth-estimation","display_name":"monocular depth estimation","score":0.9860000014305115},{"id":"https://openalex.org/keywords/diffusion-transformer","display_name":"diffusion transformer","score":0.6510000228881836},{"id":"https://openalex.org/keywords/point-cloud-generation","display_name":"point cloud generation","score":0.7590000033378601},{"id":"https://openalex.org/keywords/vision-foundation-models","display_name":"vision foundation models","score":0.9570000171661377},{"id":"https://openalex.org/keywords/stable-diffusion","display_name":"Stable Diffusion","score":0.5789999961853027}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6331999897956848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5633999705314636},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4278999865055084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42660000920295715},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38850000500679016},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2667999863624573}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/085713-5811","doi":"https://doi.org/10.52202/085713-5811","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-5811","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.07316","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.07316","pdf_url":"https://arxiv.org/pdf/2510.07316","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2510.07316","doi":"https://doi.org/10.48550/arxiv.2510.07316","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.07316","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.07316","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.07316","pdf_url":"https://arxiv.org/pdf/2510.07316","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7119825123","https://openalex.org/W7204885058","https://openalex.org/W4322760941","https://openalex.org/W4405033483","https://openalex.org/W4403947105","https://openalex.org/W4408146042","https://openalex.org/W4402753888","https://openalex.org/W4409369458","https://openalex.org/W4411631843","https://openalex.org/W4415539783"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"Pixel-Perfect":[3],"Depth,":[4],"a":[5,40],"monocular":[6],"depth":[7,23,27,44],"estimation":[8,28],"model":[9,59,138],"based":[10],"on":[11],"pixel-space":[12,82],"diffusion":[13,66,107],"generation":[14,67],"that":[15,124],"produces":[16],"high-quality,":[17],"flying-pixel-free":[18],"point":[19,159],"clouds":[20],"from":[21,98],"estimated":[22],"maps.":[24],"Current":[25],"generative":[26,146],"models":[29,101,147,156],"fine-tune":[30],"Stable":[31],"Diffusion":[32,91],"and":[33,56,119,135,151],"achieve":[34],"impressive":[35],"performance.":[36],"However,":[37],"they":[38],"require":[39],"VAE":[41],"to":[42,104,131],"compress":[43],"maps":[45],"into":[46,102],"latent":[47],"space,":[48,71],"which":[49,94],"inevitably":[50],"introduces":[51],"\\textit{flying":[52],"pixels}":[53],"at":[54],"edges":[55],"details.":[57],"Our":[58,137],"addresses":[60],"this":[61],"challenge":[62],"by":[63],"directly":[64],"performing":[65],"in":[68,157],"the":[69,77,106,127,140],"pixel":[70],"avoiding":[72],"VAE-induced":[73],"artifacts.":[74],"To":[75],"overcome":[76],"high":[78],"complexity":[79],"associated":[80],"with":[81],"generation,":[83],"we":[84],"introduce":[85],"two":[86],"novel":[87],"designs:":[88],"1)":[89],"Semantics-Prompted":[90],"Transformers":[92],"(SP-DiT),":[93],"incorporate":[95],"semantic":[96,112],"representations":[97],"vision":[99],"foundation":[100],"DiT":[103,122],"prompt":[105],"process,":[108],"thereby":[109],"preserving":[110],"global":[111],"consistency":[113],"while":[114],"enhancing":[115],"fine-grained":[116],"visual":[117],"details;":[118],"2)":[120],"Cascade":[121],"Design":[123],"progressively":[125],"increases":[126],"number":[128],"of":[129],"tokens":[130],"further":[132],"enhance":[133],"efficiency":[134],"accuracy.":[136],"achieves":[139],"best":[141],"performance":[142],"among":[143],"all":[144,154],"published":[145],"across":[148],"five":[149],"benchmarks,":[150],"significantly":[152],"outperforms":[153],"other":[155],"edge-aware":[158],"cloud":[160],"evaluation.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":38},{"year":2025,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-18T00:00:00"}
