{"id":"https://openalex.org/W3173805712","doi":"https://doi.org/10.1109/cvpr46437.2021.00549","title":"EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation","display_name":"EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3173805712","doi":"https://doi.org/10.1109/cvpr46437.2021.00549","mag":"3173805712"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr46437.2021.00549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-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/A5010965630","display_name":"Yang Jiao","orcid":"https://orcid.org/0000-0002-6390-2517"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Yang Jiao","raw_affiliation_strings":["Johns Hopkins University","Xidian Guangzhou Institute of Technology","Xidian University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Xidian Guangzhou Institute of Technology","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101413113","display_name":"Trac D. Tran","orcid":"https://orcid.org/0000-0002-0421-8416"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trac D. Tran","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101549504","display_name":"Guangming Shi","orcid":"https://orcid.org/0000-0003-2179-3292"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Shi","raw_affiliation_strings":["Xidian Guangzhou Institute of Technology","Xidian University"],"affiliations":[{"raw_affiliation_string":"Xidian Guangzhou Institute of Technology","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010965630"],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":2.4017,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.90638889,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5534","last_page":"5543"},"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":0.9973999857902527,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9951000213623047,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7725178003311157},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.735651433467865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.615746021270752},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5753997564315796},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.566383957862854},{"id":"https://openalex.org/keywords/rigidity","display_name":"Rigidity (electromagnetism)","score":0.5387374758720398},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.42534950375556946},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12132894992828369},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08972561359405518}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7725178003311157},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.735651433467865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.615746021270752},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5753997564315796},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.566383957862854},{"id":"https://openalex.org/C160343418","wikidata":"https://www.wikidata.org/wiki/Q185256","display_name":"Rigidity (electromagnetism)","level":2,"score":0.5387374758720398},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.42534950375556946},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12132894992828369},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08972561359405518},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr46437.2021.00549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W1597739853","https://openalex.org/W1612997784","https://openalex.org/W1921093919","https://openalex.org/W2010936668","https://openalex.org/W2098500213","https://openalex.org/W2115579991","https://openalex.org/W2129671742","https://openalex.org/W2133665775","https://openalex.org/W2150066425","https://openalex.org/W2150839555","https://openalex.org/W2300779272","https://openalex.org/W2507953016","https://openalex.org/W2520707372","https://openalex.org/W2548527721","https://openalex.org/W2560474170","https://openalex.org/W2604246144","https://openalex.org/W2608018946","https://openalex.org/W2609883120","https://openalex.org/W2751625733","https://openalex.org/W2768282280","https://openalex.org/W2810554001","https://openalex.org/W2890949887","https://openalex.org/W2894983388","https://openalex.org/W2904340070","https://openalex.org/W2905536983","https://openalex.org/W2949023359","https://openalex.org/W2962816904","https://openalex.org/W2963150697","https://openalex.org/W2963265330","https://openalex.org/W2963403249","https://openalex.org/W2963583471","https://openalex.org/W2963652593","https://openalex.org/W2963654727","https://openalex.org/W2963782415","https://openalex.org/W2963891416","https://openalex.org/W2963906250","https://openalex.org/W2964156315","https://openalex.org/W2964314455","https://openalex.org/W2964677288","https://openalex.org/W2964968086","https://openalex.org/W2967043539","https://openalex.org/W2984858187","https://openalex.org/W2985775862","https://openalex.org/W3034642839","https://openalex.org/W3034896357","https://openalex.org/W3094891242","https://openalex.org/W3098068165","https://openalex.org/W3109908659","https://openalex.org/W6725157647","https://openalex.org/W6736260464","https://openalex.org/W6743438356","https://openalex.org/W6746052068","https://openalex.org/W6750482691","https://openalex.org/W6752334915","https://openalex.org/W6754824001","https://openalex.org/W6755070853","https://openalex.org/W6761666624"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2147697413","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W2571255492"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,34,37,40,89,106,151,188,208],"challenging":[4],"unsupervised":[5],"scene":[6,38,49,77,195],"flow":[7,18,78,102,189,196,216],"estimation":[8,219],"problem":[9],"by":[10,58,114],"jointly":[11,59,118],"learning":[12],"four":[13],"low-level":[14],"vision":[15],"sub-tasks:":[16],"optical":[17,101,215],"F,":[19,61],"stereo-depth":[20],"D,":[21],"camera":[22,112],"pose":[23,113],"P":[24,64],"and":[25,48,63,103,109,141,174,185,205,224],"motion":[26,225],"segmentation":[27,226],"S.":[28],"Our":[29],"key":[30],"insight":[31],"is":[32,203],"that":[33,200],"rigidity":[35,52,85],"of":[36],"shares":[39],"same":[41],"inherent":[42],"geometrical":[43],"structure":[44],"with":[45,82,92,131],"object":[46],"movements":[47],"depth.":[50],"Hence,":[51],"from":[53,158],"S":[54],"can":[55],"be":[56],"inferred":[57],"coupling":[60],"D":[62],"to":[65,181,186],"achieve":[66],"more":[67],"robust":[68],"estimation.":[69],"To":[70,117,163],"this":[71],"end,":[72],"we":[73,98,122],"propose":[74],"a":[75,124],"novel":[76,125],"framework":[79],"named":[80],"EffiScene":[81],"efficient":[83],"joint":[84],"learning,":[86],"going":[87],"beyond":[88],"existing":[90],"pipeline":[91],"independent":[93],"auxiliary":[94],"structures.":[95],"In":[96],"EffiScene,":[97,166],"first":[99],"estimate":[100],"depth":[104,218],"at":[105,160],"coarse":[107],"level":[108],"then":[110],"compute":[111],"Perspective-n-Points":[115],"method.":[116],"learn":[119],"local":[120],"rigidity,":[121],"design":[123],"Rigidity":[126],"From":[127],"Motion":[128],"(RfM)":[129],"layer":[130],"three":[132],"principal":[133],"components:":[134],"(i)":[135],"correlation":[136],"extraction;":[137],"(ii)":[138],"boundary":[139,190],"learning;":[140],"(iii)":[142],"outlier":[143],"exclusion.":[144],"Final":[145],"outputs":[146],"are":[147,179],"fused":[148],"based":[149],"on":[150,194],"rigid":[152],"map":[153],"M":[154],"<inf":[155,171,176],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[156,172,177],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</inf>":[157],"RfM":[159],"finer":[161],"levels.":[162],"efficiently":[164],"train":[165],"two":[167],"new":[168],"losses":[169],"\u2112":[170,175],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">bnd</inf>":[173],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">unc</inf>":[178],"designed":[180],"prevent":[182],"trivial":[183],"solutions":[184],"regularize":[187],"discontinuity.":[191],"Extensive":[192],"experiments":[193],"benchmark":[197],"KITTI":[198],"show":[199],"our":[201],"method":[202],"effective":[204],"significantly":[206],"improves":[207],"state-of-the-art":[209],"approaches":[210],"for":[211],"all":[212],"sub-tasks,":[213],"i.e.":[214],"(5.19\u21924.20),":[217],"(3.78\u21923.46),":[220],"visual":[221],"odometry":[222],"(0.012\u21920.011)":[223],"(0.57\u2192":[227],"0.62).":[228]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}