{"id":"https://openalex.org/W4414538589","doi":"https://doi.org/10.1109/icc52391.2025.11161069","title":"Lite3D: A Lightweight Hybrid CNN-Transformer Framework for 3D Video Stabilization","display_name":"Lite3D: A Lightweight Hybrid CNN-Transformer Framework for 3D Video Stabilization","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4414538589","doi":"https://doi.org/10.1109/icc52391.2025.11161069"},"language":"en","primary_location":{"id":"doi:10.1109/icc52391.2025.11161069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","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/A5101966854","display_name":"Shan Zhang","orcid":"https://orcid.org/0000-0001-5589-2067"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zejing Shan","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025137837","display_name":"Yiping Duan","orcid":"https://orcid.org/0000-0001-9638-7112"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiping Duan","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668826","display_name":"Yue Wu","orcid":"https://orcid.org/0000-0003-0126-3614"},"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":"Yue Wu","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University,Xi'an,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024388875","display_name":"Qiyuan Du","orcid":"https://orcid.org/0000-0003-3966-080X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyuan Du","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101956410","display_name":"Liejun Wang","orcid":"https://orcid.org/0000-0002-1610-8898"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liejun Wang","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101459082","display_name":"Xiaoming Tao","orcid":"https://orcid.org/0000-0002-8763-9338"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Tao","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101966854"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25356232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3520","last_page":"3525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13579","display_name":"Image and Video Stabilization","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/T13579","display_name":"Image and Video Stabilization","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/T14158","display_name":"Optical Systems and Laser Technology","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T14510","display_name":"Medical Imaging and Analysis","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/image-stabilization","display_name":"Image stabilization","score":0.5777999758720398},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49630001187324524},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.46380001306533813},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45730000734329224},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4480000138282776},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4345000088214874},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4056999981403351}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785000205039978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7073000073432922},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.613099992275238},{"id":"https://openalex.org/C27402916","wikidata":"https://www.wikidata.org/wiki/Q31009","display_name":"Image stabilization","level":3,"score":0.5777999758720398},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.46380001306533813},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4345000088214874},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3021000027656555},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc52391.2025.11161069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5999961450","display_name":null,"funder_award_id":"61925105,62227801,62322109,62171257,U22B2001","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"stabilization":[1,32,59,105,175],"plays":[2],"a":[3,52,63],"critical":[4],"role":[5],"in":[6,38],"IoT,":[7],"as":[8],"it":[9],"enhances":[10],"the":[11,117,122,132,139,152],"accuracy":[12,37],"and":[13,21,28,66,82,93,127,177],"reliability":[14],"of":[15,113],"visual":[16],"data":[17],"collected":[18],"from":[19],"mobile":[20],"unstable":[22],"devices,":[23],"enabling":[24],"more":[25,70,110],"effective":[26],"monitoring":[27],"analysis.":[29],"However,":[30],"existing":[31,102,166],"methods":[33],"frequently":[34],"lack":[35],"sufficient":[36],"motion":[39,114],"estimation":[40],"or":[41],"struggle":[42],"with":[43,148],"expensive":[44],"computation.":[45],"In":[46,116],"this":[47],"paper,":[48],"we":[49,120],"introduce":[50],"Lite3D,":[51],"novel":[53],"lightweight":[54],"3D":[55,103,167],"deep":[56,168],"learning-based":[57,169],"video":[58,104,170],"framework":[60],"that":[61,143],"combines":[62],"hybrid":[64],"CNN":[65],"Transformer":[67],"architecture":[68],"for":[69],"efficient":[71],"feature":[72],"extraction.":[73],"During":[74],"training,":[75],"our":[76,107,159],"method":[77,160],"utilizes":[78],"estimated":[79,123],"depth":[80,134],"maps":[81],"relative":[83],"camera":[84,124],"poses":[85],"to":[86,101,165],"generate":[87],"target":[88],"views,":[89],"jointly":[90],"optimizing":[91],"DepthNet":[92],"PoseNet":[94],"through":[95],"an":[96],"unsupervised":[97],"learning":[98,112],"strategy.":[99],"Compared":[100],"methods,":[106],"approach":[108],"enables":[109],"accurate":[111],"information.":[115],"inference":[118],"phase,":[119],"smooth":[121],"pose":[125],"trajectory":[126],"synthesize":[128],"stabilized":[129],"frames":[130],"using":[131],"optimal":[133],"maps.":[135],"Experimental":[136],"results":[137],"on":[138,151],"NUS":[140],"dataset":[141,154],"demonstrate":[142],"Lite3D":[144],"achieves":[145],"state-of-the-art":[146],"stability,":[147],"additional":[149],"tests":[150],"DeepStab":[153],"confirming":[155],"strong":[156],"generalization.":[157],"Moreover,":[158],"contains":[161],"fewer":[162],"parameters":[163],"compared":[164],"stabilization,":[171],"offering":[172],"both":[173],"high":[174],"quality":[176],"computational":[178],"efficiency.":[179]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}