{"id":"https://openalex.org/W4400818973","doi":"https://doi.org/10.1145/3658236","title":"DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image","display_name":"DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image","publication_year":2024,"publication_date":"2024-07-19","ids":{"openalex":"https://openalex.org/W4400818973","doi":"https://doi.org/10.1145/3658236"},"language":"en","primary_location":{"id":"doi:10.1145/3658236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3658236","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-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/A5005810890","display_name":"Daoyi Gao","orcid":"https://orcid.org/0000-0003-0458-8107"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Daoyi Gao","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0458-8107","affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052877057","display_name":"D\u00e1vid Rozenberszki","orcid":"https://orcid.org/0000-0002-8568-4960"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Rozenberszki","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8568-4960","affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006726091","display_name":"Stefan Leutenegger","orcid":"https://orcid.org/0000-0002-7998-3737"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Leutenegger","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7998-3737","affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026634347","display_name":"Angela Dai","orcid":"https://orcid.org/0000-0002-6241-8782"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Angela Dai","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6241-8782","affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005810890"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":4.7583,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.96200746,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"43","issue":"4","first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9973000288009644,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9950000047683716,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6787394285202026},{"id":"https://openalex.org/keywords/cad","display_name":"CAD","score":0.6473278403282166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6243404746055603},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5844682455062866},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.552155077457428},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5088210701942444},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4702167809009552},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4591476619243622},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4375092387199402},{"id":"https://openalex.org/keywords/engineering-drawing","display_name":"Engineering drawing","score":0.11059227585792542}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6787394285202026},{"id":"https://openalex.org/C194789388","wikidata":"https://www.wikidata.org/wiki/Q17855283","display_name":"CAD","level":2,"score":0.6473278403282166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6243404746055603},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5844682455062866},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.552155077457428},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5088210701942444},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4702167809009552},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4591476619243622},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4375092387199402},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.11059227585792542},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3658236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3658236","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W1990345222","https://openalex.org/W2049351243","https://openalex.org/W2085261163","https://openalex.org/W2097374608","https://openalex.org/W2117539524","https://openalex.org/W2560722161","https://openalex.org/W2565639579","https://openalex.org/W2594519801","https://openalex.org/W2803973074","https://openalex.org/W2903435684","https://openalex.org/W2962785568","https://openalex.org/W2963150697","https://openalex.org/W2963892972","https://openalex.org/W2963926543","https://openalex.org/W2987505621","https://openalex.org/W2990578762","https://openalex.org/W2993195924","https://openalex.org/W3002215715","https://openalex.org/W3035398346","https://openalex.org/W3035424742","https://openalex.org/W3103740959","https://openalex.org/W3141954417","https://openalex.org/W3168433561","https://openalex.org/W3175844808","https://openalex.org/W3184081648","https://openalex.org/W3184439416","https://openalex.org/W3194468757","https://openalex.org/W3201312429","https://openalex.org/W3203887644","https://openalex.org/W4214520160","https://openalex.org/W4214625308","https://openalex.org/W4226020718","https://openalex.org/W4226082556","https://openalex.org/W4226322645","https://openalex.org/W4241602464","https://openalex.org/W4250952223","https://openalex.org/W4283775758","https://openalex.org/W4286696412","https://openalex.org/W4292794825","https://openalex.org/W4312635677","https://openalex.org/W4312912313","https://openalex.org/W4312933868","https://openalex.org/W4319302584","https://openalex.org/W4321377343","https://openalex.org/W4380053223","https://openalex.org/W4386059972","https://openalex.org/W4386075819","https://openalex.org/W4386076002","https://openalex.org/W4386076275","https://openalex.org/W4386723894","https://openalex.org/W4389334989","https://openalex.org/W4390872297","https://openalex.org/W4390873313","https://openalex.org/W4390874067","https://openalex.org/W4390874218","https://openalex.org/W4390874575","https://openalex.org/W6786276836"],"related_works":["https://openalex.org/W2334610590","https://openalex.org/W2320366403","https://openalex.org/W3204197061","https://openalex.org/W4251350712","https://openalex.org/W637098845","https://openalex.org/W2410116073","https://openalex.org/W3044972437","https://openalex.org/W4287707480","https://openalex.org/W2275866607","https://openalex.org/W3198805702"],"abstract_inverted_index":{"Perceiving":[0],"3D":[1,16],"structures":[2],"from":[3,27,84],"RGB":[4,86],"images":[5],"based":[6],"on":[7,25,137,160,172],"CAD":[8,33,64,80,104,116],"model":[9,92],"primitives":[10],"can":[11,166],"enable":[12,147],"an":[13,85,107],"effective,":[14],"efficient":[15],"object-based":[17],"representation":[18],"of":[19,32,63,98,103,113],"scenes.":[20],"However,":[21],"current":[22],"approaches":[23],"rely":[24],"supervision":[26],"expensive":[28],"yet":[29],"imperfect":[30],"annotations":[31],"models":[34,66],"associated":[35],"with":[36,178],"real":[37,68,153],"images,":[38],"and":[39,82,101,128,143],"encounter":[40],"challenges":[41],"due":[42],"to":[43,67,79,123,146,151],"the":[44,48,74,169,173],"inherent":[45],"ambiguities":[46,125],"in":[47,52,55,106,126],"task":[49],"-":[50],"both":[51],"depth-scale":[53],"ambiguity":[54],"monocular":[56,141],"perception,":[57],"as":[58,60],"well":[59],"inexact":[61,129],"matches":[62],"database":[65],"observations.":[69],"We":[70,88],"thus":[71],"propose":[72],"DiffCAD,":[73],"first":[75],"weakly-supervised":[76],"probabilistic":[77,91],"approach":[78,133,165],"retrieval":[81],"alignment":[83],"image.":[87,108],"learn":[89],"a":[90,120],"through":[93],"diffusion,":[94],"modeling":[95],"likely":[96],"distributions":[97],"shape,":[99],"pose,":[100],"scale":[102],"objects":[105],"This":[109],"enables":[110],"multi-hypothesis":[111,164],"generation":[112],"different":[114],"plausible":[115],"reconstructions,":[117],"requiring":[118],"only":[119,136],"few":[121],"hypotheses":[122],"characterize":[124],"depth/scale":[127],"shape":[130],"matches.":[131],"Our":[132],"is":[134],"trained":[135,158],"synthetic":[138,161],"data,":[139,162],"leveraging":[140],"depth":[142],"mask":[144],"estimates":[145],"robust":[148],"zero-shot":[149],"adaptation":[150],"various":[152],"target":[154],"domains.":[155],"Despite":[156],"being":[157],"solely":[159],"our":[163],"even":[167],"surpass":[168],"supervised":[170],"state-of-the-art":[171],"Scan2CAD":[174],"dataset":[175],"by":[176],"5.9%":[177],"8":[179],"hypotheses.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}