{"id":"https://openalex.org/W4394868148","doi":"https://doi.org/10.1145/3664647.3681168","title":"Digging into Contrastive Learning for Robust Depth Estimation with Diffusion Models","display_name":"Digging into Contrastive Learning for Robust Depth Estimation with Diffusion Models","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4394868148","doi":"https://doi.org/10.1145/3664647.3681168"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681168","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.09831","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102988150","display_name":"Jiyuan Wang","orcid":"https://orcid.org/0000-0002-0068-6757"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiyuan Wang","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050402282","display_name":"Chunyu Lin","orcid":"https://orcid.org/0000-0003-2847-0349"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyu Lin","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047964558","display_name":"Lang Nie","orcid":"https://orcid.org/0000-0002-7776-889X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lang Nie","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109068536","display_name":"Kang Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kang Liao","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000411800","display_name":"Shuwei Shao","orcid":"https://orcid.org/0000-0001-8057-1599"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuwei Shao","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009318707","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0001-9370-7934"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102988150"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.2493,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47151279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4129","last_page":"4137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9980000257492065,"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":0.9980000257492065,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9765999913215637,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9599000215530396,"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/computer-science","display_name":"Computer science","score":0.7614014744758606},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6760528683662415},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6109298467636108},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5648559927940369},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5288074016571045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5138704776763916},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5098244547843933},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.47275882959365845},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47059714794158936},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.442747563123703},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23767945170402527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7614014744758606},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6760528683662415},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6109298467636108},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5648559927940369},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5288074016571045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5138704776763916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5098244547843933},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.47275882959365845},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47059714794158936},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.442747563123703},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23767945170402527},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681168","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.09831","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.09831","pdf_url":"https://arxiv.org/pdf/2404.09831","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.09831","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.09831","pdf_url":"https://arxiv.org/pdf/2404.09831","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1905829557","https://openalex.org/W2905253977","https://openalex.org/W2963488291","https://openalex.org/W2963591054","https://openalex.org/W3034543232","https://openalex.org/W3194822352","https://openalex.org/W4214520160","https://openalex.org/W4321512633","https://openalex.org/W4386072275","https://openalex.org/W4386076206","https://openalex.org/W4390871805","https://openalex.org/W4390872147","https://openalex.org/W4390873354","https://openalex.org/W4401415770","https://openalex.org/W4402727668","https://openalex.org/W4402753888"],"related_works":["https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W2357409937","https://openalex.org/W2510582230","https://openalex.org/W2978674666","https://openalex.org/W2074430941","https://openalex.org/W2113096305","https://openalex.org/W2772305933","https://openalex.org/W2580722822","https://openalex.org/W3189572500"],"abstract_inverted_index":{"Recently,":[0],"diffusion-based":[1],"depth":[2,43,162],"estimation":[3,44],"methods":[4],"have":[5],"drawn":[6],"widespread":[7],"attention":[8],"due":[9],"to":[10,58,115,127],"their":[11],"elegant":[12],"denoising":[13],"patterns":[14],"and":[15,107,120,160,177,183],"promising":[16],"performance.":[17],"However,":[18],"they":[19],"are":[20,185],"typically":[21],"unreliable":[22],"under":[23],"adverse":[24],"conditions":[25],"prevalent":[26],"in":[27,62,100],"real-world":[28,178],"scenarios,":[29,141],"such":[30],"as":[31,92],"rainy,":[32],"snowy,":[33],"etc.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,66,111,142],"propose":[39],"a":[40,49,93,104,124],"novel":[41],"robust":[42,132],"method":[45],"called":[46],"D4RD,":[47],"featuring":[48],"custom":[50],"contrastive":[51,74,79],"learning":[52],"mode":[53],"tailored":[54],"for":[55],"diffusion":[56,90,149],"models":[57],"mitigate":[59],"performance":[60],"degradation":[61],"complex":[63,140],"environments.":[64],"Concretely,":[65],"integrate":[67],"the":[68,77,84,88,97,129,135,144,147],"strength":[69],"of":[70,87,131,146],"knowledge":[71],"distillation":[72],"into":[73],"learning,":[75],"building":[76],"`trinity'":[78],"scheme.":[80],"This":[81],"scheme":[82],"utilizes":[83],"sampled":[85],"noise":[86,99],"forward":[89],"process":[91],"natural":[94],"reference,":[95],"guiding":[96],"predicted":[98],"diverse":[101],"scenes":[102],"toward":[103],"more":[105,117],"stable":[106],"precise":[108],"optimum.":[109],"Moreover,":[110],"extend":[112],"noise-level":[113],"trinity":[114],"encompass":[116],"generic":[118],"feature":[119],"image":[121],"levels,":[122],"establishing":[123],"multi-level":[125],"contrast":[126],"distribute":[128],"burden":[130],"perception":[133],"across":[134],"overall":[136],"network.":[137],"Before":[138],"addressing":[139],"enhance":[143],"stability":[145],"baseline":[148],"model":[150],"with":[151],"three":[152],"straightforward":[153],"yet":[154],"effective":[155],"improvements,":[156],"which":[157],"facilitate":[158],"convergence":[159],"remove":[161],"outliers.":[163],"Extensive":[164],"experiments":[165],"demonstrate":[166],"that":[167],"D4RD":[168],"surpasses":[169],"existing":[170],"state-of-the-art":[171],"solutions":[172],"on":[173],"synthetic":[174],"corruption":[175],"datasets":[176],"weather":[179],"conditions.":[180],"Source":[181],"code":[182],"data":[184],"available":[186],"at":[187],"\\url{https://github.com/wangjiyuan9/D4RD}.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2024-04-17T00:00:00"}