{"id":"https://openalex.org/W4414359661","doi":"https://doi.org/10.24963/ijcai.2025/981","title":"DiffSQL: Leveraging Diffusion Model for Zero-Shot Self-Supervised Monocular Depth Estimation","display_name":"DiffSQL: Leveraging Diffusion Model for Zero-Shot Self-Supervised Monocular Depth Estimation","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359661","doi":"https://doi.org/10.24963/ijcai.2025/981"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/981","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Heyuan Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heyuan Zheng","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045029098","display_name":"Yunji Liang","orcid":"https://orcid.org/0000-0002-8381-8187"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunji Liang","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101818842","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0001-5145-2654"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100701166","display_name":"Zhiwen Yu","orcid":"https://orcid.org/0000-0002-9905-3238"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwen Yu","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"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":"8823","last_page":"8831"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T10638","display_name":"Optical measurement and interference techniques","score":0.9017000198364258,"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/monocular","display_name":"Monocular","score":0.7588000297546387},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7314000129699707},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6729000210762024},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5530999898910522},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4749999940395355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.454800009727478},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.38350000977516174},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35929998755455017}],"concepts":[{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7588000297546387},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7314000129699707},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6729000210762024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6628000140190125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6233000159263611},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5530999898910522},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5067999958992004},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3160000145435333},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/981","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Self-supervised":[0],"monocular":[1],"depth":[2,68],"estimation":[3,69],"has":[4],"attracted":[5],"significant":[6,19],"attention":[7],"due":[8,45],"to":[9,46,73,101],"its":[10],"broad":[11],"applications":[12],"in":[13,118,124,136],"autonomous":[14],"driving":[15],"and":[16,52,122],"robotics.":[17],"Although":[18],"performance":[20],"improvements":[21],"have":[22],"been":[23],"achieved":[24],"by":[25,95,116],"learning":[26],"the":[27,33,47,53,90,97,102,108],"relative":[28,91],"distance":[29],"of":[30,35,49,56,120,126],"objects":[31,94],"with":[32,42],"introduction":[34],"Self":[36],"Query":[37],"Layer":[38],"(SQL),":[39],"it":[40],"struggles":[41],"zero-shot":[43,137],"generalization":[44],"lack":[48],"geometric":[50,75],"features":[51],"fixed":[54],"number":[55],"query":[57,98],"sizes.":[58],"To":[59],"address":[60],"these":[61],"problems,":[62],"we":[63,81],"propose":[64],"a":[65,83],"diffusion-augmented":[66],"self-supervised":[67],"framework,":[70],"named":[71],"DiffSQL,":[72],"learn":[74],"priors":[76],"for":[77],"feature":[78,103],"augmentation.":[79],"Additionally,":[80],"introduce":[82],"dynamic":[84],"self-query":[85],"layer":[86],"that":[87,112,132],"implicitly":[88],"computes":[89],"distances":[92],"between":[93],"adjusting":[96],"size":[99],"according":[100],"distribution.":[104],"Experimental":[105],"results":[106],"on":[107],"KITTI":[109],"dataset":[110],"show":[111],"DiffSQL":[113,133],"outperforms":[114],"SQLdepth":[115],"1.03%":[117],"terms":[119,125],"AbsRel":[121],"2.79%":[123],"SqRel.":[127],"Furthermore,":[128],"our":[129],"experiments":[130],"demonstrate":[131],"is":[134],"superior":[135],"generalization.":[138]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}