{"id":"https://openalex.org/W4415023945","doi":"https://doi.org/10.1109/iccv51701.2025.01381","title":"Diving into the Fusion of Monocular Priors for Generalized Stereo Matching","display_name":"Diving into the Fusion of Monocular Priors for Generalized Stereo Matching","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415023945","doi":"https://doi.org/10.1109/iccv51701.2025.01381"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01381","doi":"https://doi.org/10.1109/iccv51701.2025.01381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01381","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.14414","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048303401","display_name":"Chengtang Yao","orcid":"https://orcid.org/0000-0001-5987-8510","observed_orcids":["https://orcid.org/0000-0001-5987-8510"]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengtang Yao","raw_affiliation_strings":["School of Computer Science & Technology, Beijing Institute of Technology,Beijing Key Laboratory of Intelligent Information Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Technology, Beijing Institute of Technology,Beijing Key Laboratory of Intelligent Information Technology,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040192942","display_name":"Lidong Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lidong Yu","raw_affiliation_strings":["NVIDIA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhidan Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhidan Liu","raw_affiliation_strings":["School of Computer Science & Technology, Beijing Institute of Technology,Beijing Key Laboratory of Intelligent Information Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Technology, Beijing Institute of Technology,Beijing Key Laboratory of Intelligent Information Technology,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113096057","display_name":"Jiaxi Zeng","orcid":"https://orcid.org/0009-0007-0481-2005","observed_orcids":["https://orcid.org/0009-0007-0481-2005"]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxi Zeng","raw_affiliation_strings":["School of Computer Science & Technology, Beijing Institute of Technology,Beijing Key Laboratory of Intelligent Information Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Technology, Beijing Institute of Technology,Beijing Key Laboratory of Intelligent Information Technology,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101888876","display_name":"Yuwei Wu","orcid":"https://orcid.org/0009-0005-4383-8748","observed_orcids":["https://orcid.org/0009-0005-4383-8748"]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Wu","raw_affiliation_strings":["School of Computer Science & Technology, Beijing Institute of Technology,Beijing Key Laboratory of Intelligent Information Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Technology, Beijing Institute of Technology,Beijing Key Laboratory of Intelligent Information Technology,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100731042","display_name":"Yunde Jia","orcid":"https://orcid.org/0000-0003-1900-8945","observed_orcids":["https://orcid.org/0000-0003-1900-8945"]},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":"CN","type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunde Jia","raw_affiliation_strings":["Shenzhen MSU-BIT University,Guangdong Laboratory of Machine Perception and Intelligent Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University,Guangdong Laboratory of Machine Perception and Intelligent Computing,China","institution_ids":["https://openalex.org/I4388482657"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2586,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.90432485,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"14887","last_page":"14897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":1.0,"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":1.0,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0,"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/stereo-matching","display_name":"stereo matching","score":0.9909999966621399},{"id":"https://openalex.org/keywords/vision-foundation-models","display_name":"vision foundation models","score":0.9330000281333923},{"id":"https://openalex.org/keywords/occlusion","display_name":"occlusion","score":0.7609999775886536},{"id":"https://openalex.org/keywords/non-lambertian-surfaces","display_name":"non-Lambertian surfaces","score":0.9739999771118164},{"id":"https://openalex.org/keywords/disparity-refinement","display_name":"disparity refinement","score":0.6259999871253967},{"id":"https://openalex.org/keywords/local-optima","display_name":"local optima","score":0.7369999885559082},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.47099998593330383}],"concepts":[{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.8166000247001648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8086000084877014},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6647999882698059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5785999894142151},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5259000062942505},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.375},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34299999475479126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.2574999928474426},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01381","doi":"https://doi.org/10.1109/iccv51701.2025.01381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01381","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.14414","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.14414","pdf_url":"https://arxiv.org/pdf/2505.14414","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":"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"},{"id":"doi:10.48550/arxiv.2505.14414","doi":"https://doi.org/10.48550/arxiv.2505.14414","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.14414","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.14414","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.14414","pdf_url":"https://arxiv.org/pdf/2505.14414","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":"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6588198453","display_name":null,"funder_award_id":"62176021,6217204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7168146166","https://openalex.org/W7163870694","https://openalex.org/W4413145021","https://openalex.org/W1997314417","https://openalex.org/W7138433632","https://openalex.org/W7084138259","https://openalex.org/W4413120545","https://openalex.org/W4405494983","https://openalex.org/W4404450527","https://openalex.org/W4214498907"],"abstract_inverted_index":{"The":[0,86,184],"matching":[1,10,45,245],"formulation":[2],"makes":[3],"it":[4],"naturally":[5],"hard":[6],"for":[7,27],"the":[8,31,41,50,55,62,70,79,82,90,106,114,117,135,145,151,165,169,178,194,199,209,217,239,253,256,270],"stereo":[9,38,44,244],"to":[11,60,121,163,192,216,242,262],"handle":[12],"ill-posed":[13,28,65],"regions":[14],"like":[15],"occlusions":[16],"and":[17,73,97,180,202,231,248,264],"non-Lambertian":[18],"surfaces.":[19],"Fusing":[20],"monocular":[21,33,52,84,95,107,130,214,240],"priors":[22],"has":[23,46],"been":[24],"proven":[25],"helpful":[26],"matching,":[29],"but":[30,139],"biased":[32],"prior":[34,53,241],"learned":[35],"from":[36,54,255,260],"small":[37],"datasets":[39,266],"constrains":[40],"generalization.":[42],"Recently,":[43],"progressed":[47],"by":[48],"leveraging":[49],"unbiased":[51],"vision":[56],"foundation":[57],"model":[58],"(VFM)":[59],"improve":[61,252],"generalization":[63],"in":[64,109,116],"regions.":[66],"We":[67,250],"dive":[68],"into":[69,172],"fusion":[71,80,127,212],"process":[72],"observe":[74],"three":[75],"main":[76],"problems":[77],"limiting":[78],"of":[81,100,128,213],"VFM":[83],"prior.":[85],"first":[87,146],"problem":[88],"is":[89,189],"misalignment":[91],"between":[92],"affine-invariant":[93],"relative":[94,175,179],"depth":[96,99,131,170,182,215],"absolute":[98,181],"disparity.":[101],"Besides,":[102],"when":[103,258],"we":[104,156,207],"use":[105],"feature":[108],"an":[110],"iterative":[111],"update":[112,119],"structure,":[113],"over-confidence":[115],"disparity":[118,141,196,218],"leads":[120],"local":[122,136,160,186,200],"optima":[123,137,201],"results.":[124],"A":[125],"direct":[126,211],"a":[129,158,173,220,224],"map":[132,162,171,188],"could":[133],"alleviate":[134],"problem,":[138,222],"noisy":[140,203],"results":[142,246],"computed":[143,185],"at":[144],"several":[147],"iterations":[148],"will":[149],"misguide":[150],"fusion.":[152],"In":[153,205],"this":[154],"paper,":[155],"propose":[157],"binary":[159,174],"ordering":[161,187],"guide":[164],"fusion,":[166],"which":[167],"converts":[168],"format,":[176],"unifying":[177],"representation.":[183],"also":[190],"used":[191],"re-weight":[193],"initial":[195],"update,":[197],"resolving":[198],"problem.":[204],"addition,":[206],"formulate":[208],"final":[210],"as":[219],"registration":[221],"where":[223],"pixel-wise":[225],"linear":[226],"regression":[227],"module":[228],"can":[229],"globally":[230],"adaptively":[232],"align":[233],"them.":[234],"Our":[235],"method":[236],"fully":[237],"exploits":[238],"support":[243],"effectively":[247],"efficiently.":[249],"significantly":[251],"performance":[254],"experiments":[257],"generalizing":[259],"SceneFlow":[261],"Middlebury":[263],"Booster":[265],"while":[267],"barely":[268],"reducing":[269],"efficiency.":[271]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2025-10-10T00:00:00"}