{"id":"https://openalex.org/W4406259227","doi":"https://doi.org/10.1109/tmm.2024.3521846","title":"Uni-DPM: Unifying Self-Supervised Monocular Depth, Pose, and Object Motion Estimation With a Shared Representation","display_name":"Uni-DPM: Unifying Self-Supervised Monocular Depth, Pose, and Object Motion Estimation With a Shared Representation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406259227","doi":"https://doi.org/10.1109/tmm.2024.3521846"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521846","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","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/A5102819846","display_name":"Guanghui Wu","orcid":"https://orcid.org/0000-0003-3646-2568"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghui Wu","raw_affiliation_strings":["School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China","School of Electronics and Communication Engineering, the Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University (SYSU), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3646-2568","affiliations":[{"raw_affiliation_string":"School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Communication Engineering, the Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University (SYSU), Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040669893","display_name":"Lili Chen","orcid":"https://orcid.org/0000-0002-5958-7243"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lili Chen","raw_affiliation_strings":["Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Zengping Chen","orcid":"https://orcid.org/0000-0002-2892-8252"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengping Chen","raw_affiliation_strings":["School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China","School of Electronics and Communication Engineering, the Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University (SYSU), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2892-8252","affiliations":[{"raw_affiliation_string":"School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Communication Engineering, the Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University (SYSU), Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66355412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"27","issue":null,"first_page":"1498","last_page":"1511"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9998999834060669,"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":0.9998999834060669,"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/T10638","display_name":"Optical measurement and interference techniques","score":0.9869999885559082,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9860000014305115,"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":0.8529236316680908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7068228125572205},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6386345624923706},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5590340495109558},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.556667685508728},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5391481518745422},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5218707323074341},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48645445704460144},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.48472166061401367},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.47578513622283936},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3825858235359192},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33305248618125916},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09664011001586914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8529236316680908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7068228125572205},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6386345624923706},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5590340495109558},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.556667685508728},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5391481518745422},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5218707323074341},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48645445704460144},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.48472166061401367},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47578513622283936},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3825858235359192},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33305248618125916},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09664011001586914},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521846","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G622858442","display_name":null,"funder_award_id":"62372491","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6790872277","display_name":null,"funder_award_id":"61972435","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7593575001","display_name":null,"funder_award_id":"2022B1515020103","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G8252004906","display_name":null,"funder_award_id":"U20A20185","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"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":100,"referenced_works":["https://openalex.org/W1508115313","https://openalex.org/W1903029394","https://openalex.org/W1921093919","https://openalex.org/W2087921381","https://openalex.org/W2088692258","https://openalex.org/W2098500213","https://openalex.org/W2115579991","https://openalex.org/W2128019145","https://openalex.org/W2129671742","https://openalex.org/W2133665775","https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2259424905","https://openalex.org/W2340897893","https://openalex.org/W2520707372","https://openalex.org/W2535547924","https://openalex.org/W2565639579","https://openalex.org/W2609883120","https://openalex.org/W2741885505","https://openalex.org/W2793114969","https://openalex.org/W2810554001","https://openalex.org/W2885010430","https://openalex.org/W2887479417","https://openalex.org/W2890949887","https://openalex.org/W2935854115","https://openalex.org/W2942395934","https://openalex.org/W2949023359","https://openalex.org/W2962816904","https://openalex.org/W2963210183","https://openalex.org/W2963265330","https://openalex.org/W2963412495","https://openalex.org/W2963549785","https://openalex.org/W2963583471","https://openalex.org/W2963654727","https://openalex.org/W2963906250","https://openalex.org/W2964314455","https://openalex.org/W2964677288","https://openalex.org/W2964968086","https://openalex.org/W2967321219","https://openalex.org/W2974576232","https://openalex.org/W2981732213","https://openalex.org/W2982014906","https://openalex.org/W2982102242","https://openalex.org/W2985178537","https://openalex.org/W2985775862","https://openalex.org/W3034364596","https://openalex.org/W3034403088","https://openalex.org/W3034428934","https://openalex.org/W3034530552","https://openalex.org/W3034564916","https://openalex.org/W3034604951","https://openalex.org/W3034642839","https://openalex.org/W3048510980","https://openalex.org/W3060975791","https://openalex.org/W3081015685","https://openalex.org/W3107156787","https://openalex.org/W3108086282","https://openalex.org/W3120407065","https://openalex.org/W3171953850","https://openalex.org/W3173409262","https://openalex.org/W3173561529","https://openalex.org/W3173805712","https://openalex.org/W3174211490","https://openalex.org/W3175682855","https://openalex.org/W3176063055","https://openalex.org/W3180787238","https://openalex.org/W3194533273","https://openalex.org/W3203073814","https://openalex.org/W3204559841","https://openalex.org/W3205269569","https://openalex.org/W3206941470","https://openalex.org/W3212877081","https://openalex.org/W4206342640","https://openalex.org/W4206545998","https://openalex.org/W4226179628","https://openalex.org/W4226267082","https://openalex.org/W4290713684","https://openalex.org/W4303650407","https://openalex.org/W4308480793","https://openalex.org/W4312253171","https://openalex.org/W4312366155","https://openalex.org/W4312398233","https://openalex.org/W4312572946","https://openalex.org/W4312748209","https://openalex.org/W4313040116","https://openalex.org/W4313477588","https://openalex.org/W4365420337","https://openalex.org/W4382239999","https://openalex.org/W4386075945","https://openalex.org/W4387415226","https://openalex.org/W4390204136","https://openalex.org/W4392693764","https://openalex.org/W6631190155","https://openalex.org/W6685261749","https://openalex.org/W6771531989","https://openalex.org/W6780320512","https://openalex.org/W6784135996","https://openalex.org/W6785257420","https://openalex.org/W6785345353","https://openalex.org/W6791097704"],"related_works":["https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W4387967917","https://openalex.org/W200819717","https://openalex.org/W4387968151","https://openalex.org/W4307623796","https://openalex.org/W4394784820","https://openalex.org/W2030154815","https://openalex.org/W3005839910","https://openalex.org/W2051121715"],"abstract_inverted_index":{"Self-supervised":[0],"monocular":[1,21],"depth":[2],"estimation":[3],"has":[4],"been":[5],"widely":[6],"studied":[7],"for":[8,36,145],"3D":[9],"perception,":[10],"as":[11],"it":[12],"can":[13],"infer":[14],"depth,":[15],"pose,":[16],"and":[17,26,62,73,79,125,172],"object":[18],"motion":[19,173],"from":[20],"videos.":[22],"However,":[23],"existing":[24],"single-view":[25],"multi-view":[27],"methods":[28,61],"employ":[29],"separate":[30],"networks":[31],"to":[32,97,112,164],"learn":[33],"specific":[34],"representations":[35,82],"these":[37,68,88,99,146,184],"different":[38,81,154],"tasks.":[39,135],"This":[40],"not":[41],"only":[42],"results":[43],"in":[44],"a":[45,93,103,139],"cumbersome":[46],"model":[47,111],"architecture":[48],"but":[49],"also":[50,189],"limits":[51],"the":[52,64,128,132,151,178],"representation":[53,144],"capacity.":[54],"In":[55,158],"this":[56],"paper,":[57],"we":[58,90,107,137],"revisit":[59],"previous":[60],"have":[63],"following":[65],"insights:":[66],"(1)":[67],"three":[69,100,147],"tasks":[70,101,116,148],"are":[71],"reciprocal":[72],"all":[74],"depend":[75],"on":[76,87,122,183],"matching":[77,123],"information;":[78],"(2)":[80],"carry":[83],"complementary":[84],"information.":[85,157],"Based":[86],"insights,":[89],"propose":[91],"Uni-DPM,":[92],"compact":[94],"self-supervised":[95],"framework":[96],"complete":[98,114],"with":[102],"shared":[104,140],"representation.":[105],"Specifically,":[106],"introduce":[108],"an":[109],"U-net-like":[110],"synchronously":[113],"multiple":[115],"by":[117,130,149],"leveraging":[118],"their":[119],"common":[120],"dependence":[121],"information,":[124],"iteratively":[126],"refine":[127],"predictions":[129],"utilizing":[131],"reciprocity":[133],"among":[134,153],"Furthermore,":[136],"design":[138],"Appearance-":[141],"Matching-Temporal":[142],"(AMT)":[143],"exploiting":[150],"complementarity":[152],"types":[155],"of":[156,180],"addition,":[159],"our":[160,181,191],"Uni-DPM":[161,182],"is":[162],"scalable":[163],"downstream":[165],"tasks,":[166,185],"including":[167],"scene":[168],"flow,":[169,171],"optical":[170],"segmentation.":[174],"Comparative":[175],"experiments":[176,188],"demonstrate":[177],"competitiveness":[179],"while":[186],"ablation":[187],"verify":[190],"insights.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}