{"id":"https://openalex.org/W4414359917","doi":"https://doi.org/10.24963/ijcai.2025/221","title":"Self-supervised End-to-end ToF Imaging Based on RGB-D Cross-modal Dependency","display_name":"Self-supervised End-to-end ToF Imaging Based on RGB-D Cross-modal Dependency","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359917","doi":"https://doi.org/10.24963/ijcai.2025/221"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/221","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/221","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":"https://openalex.org/A5101891769","display_name":"Weihang Wang","orcid":"https://orcid.org/0000-0003-0675-7402"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weihang Wang","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087368642","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0001-9115-3755"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101631903","display_name":"Wen Fei","orcid":"https://orcid.org/0000-0002-1682-4480"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wen","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"1982","last_page":"1990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12153","display_name":"Advanced Optical Sensing Technologies","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12153","display_name":"Advanced Optical Sensing Technologies","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10638","display_name":"Optical measurement and interference techniques","score":0.9905999898910522,"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/T13049","display_name":"Surface Roughness and Optical Measurements","score":0.9818999767303467,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7300000190734863},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5803999900817871},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5194000005722046},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.43869999051094055},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4203000068664551},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41909998655319214},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.41760000586509705},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4108999967575073},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7300000190734863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139000296592712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6288999915122986},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5803999900817871},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4472000002861023},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C35772409","wikidata":"https://www.wikidata.org/wiki/Q1323086","display_name":"Image noise","level":3,"score":0.33000001311302185},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2987000048160553},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29249998927116394},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C193519340","wikidata":"https://www.wikidata.org/wiki/Q891179","display_name":"Data loss","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/221","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/221","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":{"Time-of-Flight":[0],"(ToF)":[1],"imaging":[2,19],"systems":[3],"are":[4],"susceptible":[5],"to":[6,27,53,107,148],"various":[7,90],"noise":[8,64,110,130],"and":[9,62,101,111,131,138],"degradation,":[10],"which":[11,79],"can":[12],"severely":[13],"affect":[14],"image":[15,39,113],"quality.":[16],"Traditional":[17],"sequential":[18],"pipelines":[20],"often":[21],"suffer":[22],"from":[23],"error":[24],"accumulation":[25],"due":[26,52],"separate":[28],"multi-stage":[29],"processing.":[30],"Existing":[31],"end-to-end":[32,76],"methods":[33],"typically":[34],"rely":[35],"on":[36,135],"noisy-clean":[37,84,154],"depth":[38,102],"pairs":[40,85],"for":[41,75,156],"supervised":[42,149],"learning.":[43],"However,":[44],"acquiring":[45],"ground-truth":[46],"is":[47,175],"challenging":[48],"in":[49],"real-world":[50,139],"scenarios":[51],"factors":[54],"such":[55],"as":[56,104],"Multi-Path":[57],"Interference":[58],"(MPI),":[59],"phase":[60],"wrapping,":[61],"complex":[63],"patterns.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"propose":[70],"a":[71],"self-supervised":[72],"learning":[73],"framework":[74,94],"ToF":[77],"imaging,":[78],"does":[80],"not":[81],"require":[82],"any":[83],"yet":[86],"generalizes":[87],"well":[88],"across":[89,165],"off-the-shelf":[91],"cameras.":[92],"Our":[93],"leverages":[95],"the":[96,116,120],"cross-modal":[97],"dependencies":[98],"between":[99],"RGB":[100],"data":[103,140,155],"implicit":[105],"supervision":[106],"effectively":[108],"suppress":[109],"maintain":[112],"fidelity.":[114],"Additionally,":[115],"loss":[117],"function":[118],"integrates":[119],"statistical":[121],"characteristics":[122],"of":[123],"raw":[124],"measurement":[125],"data,":[126],"enhancing":[127],"robustness":[128],"against":[129],"artifacts.":[132],"Extensive":[133],"experiments":[134],"both":[136],"synthetic":[137],"demonstrate":[141],"that":[142],"our":[143,159],"approach":[144],"achieves":[145],"performance":[146,164],"comparable":[147],"methods,":[150],"without":[151],"requiring":[152],"paired":[153],"training.":[157],"Furthermore,":[158],"method":[160],"consistently":[161],"delivers":[162],"strong":[163],"all":[166],"evaluated":[167],"cameras,":[168],"highlighting":[169],"its":[170],"generalization":[171],"capabilities.":[172],"The":[173],"code":[174],"available":[176],"at":[177],"https://github.com/WeihangWANG/RGBD_imaging.":[178]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}