{"id":"https://openalex.org/W4416097394","doi":"https://doi.org/10.1109/iccv51701.2025.01260","title":"Auto-Regressive Transformation for Image Alignment","display_name":"Auto-Regressive Transformation for Image Alignment","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416097394","doi":"https://doi.org/10.1109/iccv51701.2025.01260"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.04864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088627802","display_name":"K. Lee","orcid":"https://orcid.org/0009-0001-6530-4764"},"institutions":[{"id":"https://openalex.org/I4210123907","display_name":"National University College","ror":"https://ror.org/02hs8e066","country_code":"PR","type":"education","lineage":["https://openalex.org/I4210123907"]}],"countries":["PR"],"is_corresponding":false,"raw_author_name":"Kanggeon Lee","raw_affiliation_strings":["ASRI, Seoul National University,Dept. of ECE,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASRI, Seoul National University,Dept. of ECE,Korea","institution_ids":["https://openalex.org/I4210123907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079384927","display_name":"Soochahn Lee","orcid":"https://orcid.org/0000-0002-2975-2519"},"institutions":[{"id":"https://openalex.org/I110273157","display_name":"Kookmin University","ror":"https://ror.org/0049erg63","country_code":"KR","type":"education","lineage":["https://openalex.org/I110273157"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soochahn Lee","raw_affiliation_strings":["Kookmin University,Dept. of Electronics Engineering,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kookmin University,Dept. of Electronics Engineering,Korea","institution_ids":["https://openalex.org/I110273157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046504049","display_name":"Kyoung Mu Lee","orcid":"https://orcid.org/0000-0001-7210-1036"},"institutions":[{"id":"https://openalex.org/I4210123907","display_name":"National University College","ror":"https://ror.org/02hs8e066","country_code":"PR","type":"education","lineage":["https://openalex.org/I4210123907"]}],"countries":["PR"],"is_corresponding":false,"raw_author_name":"Kyoung Mu Lee","raw_affiliation_strings":["ASRI, Seoul National University,Dept. of ECE,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASRI, Seoul National University,Dept. of ECE,Korea","institution_ids":["https://openalex.org/I4210123907"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30825094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13569","last_page":"13579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.32659998536109924,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.32659998536109924,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1282999962568283,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09700000286102295,"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/robustness","display_name":"Robustness (evolution)","score":0.738099992275238},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6115999817848206},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5184000134468079},{"id":"https://openalex.org/keywords/image-registration","display_name":"Image registration","score":0.44999998807907104},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4185999929904938},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.385699987411499},{"id":"https://openalex.org/keywords/geometric-transformation","display_name":"Geometric transformation","score":0.3822000026702881}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.738099992275238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6462000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6133000254631042},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6115999817848206},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5149999856948853},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.44999998807907104},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C56435381","wikidata":"https://www.wikidata.org/wiki/Q1196371","display_name":"Geometric transformation","level":3,"score":0.3822000026702881},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3652999997138977},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C126795593","wikidata":"https://www.wikidata.org/wiki/Q7333813","display_name":"Rigid transformation","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.2897000014781952},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2847999930381775},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.04864","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.04864","pdf_url":"https://arxiv.org/pdf/2505.04864","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.04864","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.04864","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.04864","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.04864","pdf_url":"https://arxiv.org/pdf/2505.04864","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G120689132","display_name":null,"funder_award_id":"RS-2025-02219317","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G2206577141","display_name":null,"funder_award_id":"RS-2024-00432410","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"},{"id":"https://openalex.org/G2206812781","display_name":null,"funder_award_id":"2021-0-02068","funder_id":"https://openalex.org/F4320321292","funder_display_name":"Seoul National University"},{"id":"https://openalex.org/G3098371196","display_name":null,"funder_award_id":"2021-0-01343","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4059824282","display_name":null,"funder_award_id":"2021-0-02068,2023-0-00156,RS-2025-02219317","funder_id":"https://openalex.org/F4320321292","funder_display_name":"Seoul National University"},{"id":"https://openalex.org/G4195339926","display_name":null,"funder_award_id":"RS-2025-00521972","funder_id":"https://openalex.org/F4320321253","funder_display_name":"Kookmin University"},{"id":"https://openalex.org/G4643994530","display_name":null,"funder_award_id":"2021-0-02068","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5635159257","display_name":null,"funder_award_id":"2021-0-01343","funder_id":"https://openalex.org/F4320321292","funder_display_name":"Seoul National University"},{"id":"https://openalex.org/G6203074121","display_name":null,"funder_award_id":"2023-0-00156","funder_id":"https://openalex.org/F4320321292","funder_display_name":"Seoul National University"},{"id":"https://openalex.org/G7169510715","display_name":null,"funder_award_id":"2021-0-02068","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"},{"id":"https://openalex.org/G900347928","display_name":null,"funder_award_id":"2021-0-01343","funder_id":"https://openalex.org/F4320319144","funder_display_name":"Indian Institute of Technology, Patna"}],"funders":[{"id":"https://openalex.org/F4320319144","display_name":"Indian Institute of Technology, Patna","ror":"https://ror.org/01ft5vz71"},{"id":"https://openalex.org/F4320321253","display_name":"Kookmin University","ror":"https://ror.org/0049erg63"},{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416097394.pdf","grobid_xml":"https://content.openalex.org/works/W4416097394.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"methods":[1,113],"for":[2,133],"image":[3,45,135],"alignment":[4,99],"struggle":[5],"in":[6,21,43,101],"cases":[7],"involving":[8],"feature-sparse":[9],"regions,":[10,96],"extreme":[11],"scale":[12],"and":[13,16,117,130],"field-of-view":[14],"differences,":[15],"large":[17],"deformations,":[18],"often":[19],"resulting":[20],"suboptimal":[22],"accuracy.":[23],"Robustness":[24],"to":[25],"these":[26],"challenges":[27],"can":[28],"be":[29],"improved":[30],"through":[31,62],"iterative":[32],"refinement":[33],"of":[34],"the":[35,59,73,88,91],"transform":[36,74],"field":[37,75],"while":[38],"focusing":[39],"on":[40,94,114,121],"critical":[41,95],"regions":[42],"multi-scale":[44,68],"representations.":[46],"We":[47],"thus":[48],"propose":[49],"Auto-Regressive":[50],"Transformation":[51],"(ART),":[52],"a":[53,128],"novel":[54],"method":[55],"that":[56,108],"iteratively":[57],"estimates":[58],"coarse-to-fine":[60],"transformations":[61],"an":[63],"auto-regressive":[64],"pipeline.":[65],"Leveraging":[66],"hierarchical":[67],"features,":[69],"our":[70],"network":[71],"refines":[72],"parameters":[76],"using":[77],"randomly":[78],"sampled":[79],"points":[80],"at":[81],"each":[82],"scale.":[83],"By":[84],"incorporating":[85],"guidance":[86],"from":[87],"cross-attention":[89],"layer,":[90],"model":[92],"focuses":[93],"ensuring":[97],"accurate":[98],"even":[100],"challenging,":[102],"feature-limited":[103],"conditions.":[104],"Extensive":[105],"experiments":[106],"demonstrate":[107],"ART":[109],"significantly":[110],"outperforms":[111],"state-of-the-art":[112],"planar":[115],"images":[116],"achieves":[118],"comparable":[119],"performance":[120],"3D":[122],"scene":[123],"images,":[124],"establishing":[125],"it":[126],"as":[127],"powerful":[129],"versatile":[131],"solution":[132],"precise":[134],"alignment.":[136]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}