{"id":"https://openalex.org/W7164823868","doi":"https://doi.org/10.1145/3805622.3810718","title":"MMRet3D: A Multi-Modal Matching Framework for 3D Object Retrieval from Multi-View Images","display_name":"MMRet3D: A Multi-Modal Matching Framework for 3D Object Retrieval from Multi-View Images","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164823868","doi":"https://doi.org/10.1145/3805622.3810718"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810718","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810718","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810718","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057923247","display_name":"Zeyu Li","orcid":"https://orcid.org/0000-0003-0335-2469"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0335-2469","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440301","display_name":"Lei Li","orcid":"https://orcid.org/0000-0002-3204-6527"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3204-6527","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92255586,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"337","last_page":"346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.5022000074386597,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.5022000074386597,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.3154999911785126,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.04259999841451645,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5351999998092651},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5203999876976013},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4878999888896942},{"id":"https://openalex.org/keywords/cad","display_name":"CAD","score":0.47620001435279846},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4722999930381775},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45010000467300415},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4309000074863434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42660000920295715}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7470999956130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6814000010490417},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.657800018787384},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5351999998092651},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C194789388","wikidata":"https://www.wikidata.org/wiki/Q17855283","display_name":"CAD","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4722999930381775},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3628999888896942},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3450999855995178},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.30489999055862427},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C136520226","wikidata":"https://www.wikidata.org/wiki/Q302814","display_name":"Geometric data analysis","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810718","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810718","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810718","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810718","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7161765694618225}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1513100184","https://openalex.org/W1644641054","https://openalex.org/W2194775991","https://openalex.org/W2342223463","https://openalex.org/W2594519801","https://openalex.org/W2798927139","https://openalex.org/W2885364117","https://openalex.org/W2903435684","https://openalex.org/W2950212750","https://openalex.org/W2963627347","https://openalex.org/W2979750740","https://openalex.org/W2981932175","https://openalex.org/W3034346071","https://openalex.org/W3035154952","https://openalex.org/W3035424742","https://openalex.org/W3102061158","https://openalex.org/W3108800063","https://openalex.org/W3199238138","https://openalex.org/W3203887644","https://openalex.org/W4294959213","https://openalex.org/W4297903107","https://openalex.org/W4386075660","https://openalex.org/W4386076097","https://openalex.org/W4389348109","https://openalex.org/W4389539488","https://openalex.org/W4390873542","https://openalex.org/W4395481595","https://openalex.org/W4402354170","https://openalex.org/W4402733576","https://openalex.org/W4402753888","https://openalex.org/W4402753900","https://openalex.org/W4402773116","https://openalex.org/W4404526392","https://openalex.org/W4412396192","https://openalex.org/W4413038277","https://openalex.org/W4413145659","https://openalex.org/W4413146128","https://openalex.org/W4413147177","https://openalex.org/W4413156414","https://openalex.org/W4416999390","https://openalex.org/W4417085408","https://openalex.org/W7133205985","https://openalex.org/W7133246057"],"related_works":[],"abstract_inverted_index":{"Retrieval-based":[0],"3D":[1,50,110,117],"scene":[2,152],"reconstruction":[3],"has":[4,142],"become":[5],"a":[6,29,68,80,143],"practical":[7],"paradigm":[8],"for":[9,71],"building":[10],"indoor":[11],"environments":[12],"from":[13,19,75,84],"RGB":[14],"observations":[15,100],"by":[16,57,97],"assembling":[17],"objects":[18,44],"large":[20],"CAD":[21,26,73,106],"repositories.":[22],"However,":[23],"accurate":[24],"instance-level":[25,72,139],"retrieval":[27,74,124,140],"remains":[28],"critical":[30],"bottleneck.":[31],"Existing":[32],"RGB-based":[33],"matching":[34,96],"pipelines":[35],"are":[36],"vulnerable":[37],"to":[38,47,118],"appearance-shape":[39],"ambiguity,":[40],"where":[41],"visually":[42],"similar":[43],"may":[45],"correspond":[46],"substantially":[48],"different":[49],"geometries,":[51],"and":[52,59,92,130,141],"the":[53,136,148],"problem":[54],"is":[55],"amplified":[56],"occlusion":[58],"viewpoint":[60],"bias":[61],"in":[62,116],"real-world":[63],"scans.":[64],"We":[65],"propose":[66],"MMRet3D,":[67],"geometry-consistent":[69],"framework":[70],"multi-view":[76,99,114],"images.":[77],"MMRet3D":[78,134],"learns":[79],"retrieval-oriented":[81],"geometric":[82],"descriptor":[83],"surface-normal":[85],"cues":[86],"via":[87],"Geometric":[88],"Knowledge":[89],"Distillation":[90],"(GKD)":[91],"performs":[93],"viewpoint-aligned":[94],"multi-modal":[95],"comparing":[98],"with":[101],"pose-aligned":[102],"renderings":[103],"of":[104,138,150],"candidate":[105],"models.":[107],"In":[108],"addition,":[109],"Gaussian":[111],"Clustering":[112],"fuses":[113],"semantics":[115],"obtain":[119],"view-consistent":[120],"object":[121],"instances":[122],"as":[123],"queries.":[125],"Experiments":[126],"on":[127,147],"Scan2CAD,":[128],"ScanNet,":[129],"Sintel":[131],"demonstrate":[132],"that":[133],"enhances":[135],"accuracy":[137],"continuous":[144],"positive":[145],"impact":[146],"quality":[149],"downstream":[151],"reconstruction.":[153]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}