{"id":"https://openalex.org/W4416748923","doi":"https://doi.org/10.1109/iros60139.2025.11247705","title":"ViewActive: Active viewpoint optimization from a single image","display_name":"ViewActive: Active viewpoint optimization from a single image","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748923","doi":"https://doi.org/10.1109/iros60139.2025.11247705"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5106236833","display_name":"Jiayi Wu","orcid":"https://orcid.org/0000-0001-9330-4836"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiayi Wu","raw_affiliation_strings":["University of Maryland Institute for Advanced Computer Studies, University of Maryland,Perception and Robotics Group,College Park,MD,USA,20742"],"affiliations":[{"raw_affiliation_string":"University of Maryland Institute for Advanced Computer Studies, University of Maryland,Perception and Robotics Group,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101610451","display_name":"Xiaomin Lin","orcid":"https://orcid.org/0000-0002-9764-5168"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaomin Lin","raw_affiliation_strings":["University of Maryland Institute for Advanced Computer Studies, University of Maryland,Perception and Robotics Group,College Park,MD,USA,20742"],"affiliations":[{"raw_affiliation_string":"University of Maryland Institute for Advanced Computer Studies, University of Maryland,Perception and Robotics Group,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102487388","display_name":"Botao He","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Botao He","raw_affiliation_strings":["University of Maryland Institute for Advanced Computer Studies, University of Maryland,Perception and Robotics Group,College Park,MD,USA,20742"],"affiliations":[{"raw_affiliation_string":"University of Maryland Institute for Advanced Computer Studies, University of Maryland,Perception and Robotics Group,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105899355","display_name":"Cornelia Ferm\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cornelia Ferm\u00fcller","raw_affiliation_strings":["University of Maryland Institute for Advanced Computer Studies, University of Maryland,Perception and Robotics Group,College Park,MD,USA,20742"],"affiliations":[{"raw_affiliation_string":"University of Maryland Institute for Advanced Computer Studies, University of Maryland,Perception and Robotics Group,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036912867","display_name":"Yiannis Aloimonos","orcid":"https://orcid.org/0000-0002-8152-4281"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiannis Aloimonos","raw_affiliation_strings":["University of Maryland Institute for Advanced Computer Studies, University of Maryland,Perception and Robotics Group,College Park,MD,USA,20742"],"affiliations":[{"raw_affiliation_string":"University of Maryland Institute for Advanced Computer Studies, University of Maryland,Perception and Robotics Group,College Park,MD,USA,20742","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5106236833"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":5.6224,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96526843,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11812","last_page":"11818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.20020000636577606,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.20020000636577606,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.18809999525547028,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11379999667406082,"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/viewpoints","display_name":"Viewpoints","score":0.6600000262260437},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5422000288963318},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.539900004863739},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5209000110626221},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5128999948501587},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49869999289512634},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4424000084400177},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.39879998564720154},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.38589999079704285}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7360000014305115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7121000289916992},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.6600000262260437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6460000276565552},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.539900004863739},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5209000110626221},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49869999289512634},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4424000084400177},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.37599998712539673},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.35690000653266907},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3465000092983246},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1986570437","https://openalex.org/W2005168270","https://openalex.org/W2019336354","https://openalex.org/W2036439337","https://openalex.org/W2079745210","https://openalex.org/W2087825138","https://openalex.org/W2090278863","https://openalex.org/W2106874266","https://openalex.org/W2108598243","https://openalex.org/W2131499409","https://openalex.org/W2137372226","https://openalex.org/W2299529128","https://openalex.org/W2342834908","https://openalex.org/W2950069298","https://openalex.org/W2963785592","https://openalex.org/W3035237020","https://openalex.org/W3035444404","https://openalex.org/W3109585842","https://openalex.org/W3138270694","https://openalex.org/W3149657477","https://openalex.org/W4220944761","https://openalex.org/W4248601629","https://openalex.org/W4320002812","https://openalex.org/W4383109003","https://openalex.org/W4385485159","https://openalex.org/W4386075660","https://openalex.org/W4401415258","https://openalex.org/W4402260841","https://openalex.org/W4405785168","https://openalex.org/W4405786822","https://openalex.org/W4408358833","https://openalex.org/W4413257398"],"related_works":[],"abstract_inverted_index":{"When":[0],"observing":[1],"objects,":[2,160],"humans":[3],"benefit":[4],"from":[5,77],"their":[6],"spatial":[7],"visualization":[8],"and":[9,33,44,104,129,141,183,196],"mental":[10],"rotation":[11],"ability":[12],"to":[13,30,112,137,155],"envision":[14],"potential":[15],"optimal":[16,40],"viewpoints":[17,41],"based":[18,85],"on":[19,87,170],"the":[20,88,96,149,176],"current":[21,89],"observation.":[22],"This":[23],"capability":[24],"is":[25],"crucial":[26],"for":[27,47,107,191],"enabling":[28],"robots":[29,59],"achieve":[31],"efficient":[32],"robust":[34,139],"scene":[35],"perception":[36],"during":[37],"operation,":[38],"as":[39],"provide":[42],"essential":[43],"informative":[45],"features":[46],"accurately":[48],"representing":[49],"scenes":[50],"in":[51],"2D":[52,90],"images,":[53],"thereby":[54],"enhancing":[55],"downstream":[56],"tasks.To":[57],"endow":[58],"with":[60],"this":[61],"human-like":[62],"active":[63],"viewpoint":[64,82,108,120],"optimization":[65,83],"capability,":[66],"we":[67,94],"propose":[68],"ViewActive,":[69],"a":[70,102,171],"modernized":[71],"machine":[72],"learning":[73],"approach":[74],"drawing":[75],"inspiration":[76],"aspect":[78,114],"graph,":[79,115],"which":[80,144],"provides":[81],"guidance":[84],"solely":[86],"image":[91,135],"input.":[92],"Specifically,":[93],"introduce":[95],"3D":[97,150],"Viewpoint":[98],"Quality":[99],"Field":[100],"(VQF),":[101],"compact":[103],"consistent":[105],"representation":[106],"quality":[109,121],"distribution":[110],"similar":[111],"an":[113],"composed":[116],"of":[117,178],"three":[118],"general-purpose":[119],"metrics:":[122],"self-occlusion":[123],"ratio,":[124],"occupancy-aware":[125],"surface":[126],"normal":[127],"entropy,":[128],"visual":[130,140],"entropy.":[131],"We":[132],"utilize":[133],"pre-trained":[134],"encoders":[136],"extract":[138],"semantic":[142],"features,":[143],"are":[145,198],"then":[146],"decoded":[147],"into":[148,187],"VQF,":[151],"allowing":[152],"our":[153],"model":[154],"generalize":[156],"effectively":[157],"across":[158],"diverse":[159],"including":[161],"unseen":[162],"categories.":[163],"The":[164],"lightweight":[165],"ViewActive":[166],"network":[167],"(72":[168],"FPS":[169],"single":[172],"GPU)":[173],"significantly":[174],"enhances":[175],"performance":[177],"state-of-the-art":[179],"object":[180],"recognition":[181],"pipelines":[182],"can":[184],"be":[185],"integrated":[186],"real-time":[188],"motion":[189],"planning":[190],"robotic":[192],"applications.":[193],"Our":[194],"code":[195],"dataset":[197],"available":[199],"here":[200],"https://github.com/jiayi-wu-umd/ViewActive.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}
