{"id":"https://openalex.org/W4417125575","doi":"https://doi.org/10.1145/3757377.3763891","title":"Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization","display_name":"Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417125575","doi":"https://doi.org/10.1145/3757377.3763891"},"language":null,"primary_location":{"id":"doi:10.1145/3757377.3763891","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","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/A5100658703","display_name":"Yang You","orcid":"https://orcid.org/0000-0003-0125-0792"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yang You","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052260671","display_name":"Mikaela Angelina Uy","orcid":"https://orcid.org/0009-0009-4917-7724"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Mikaela Angelina Uy","raw_affiliation_strings":["Stanford University, Stanford, USA and NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA and NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaqi Han","orcid":"https://orcid.org/0009-0004-5285-3889"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Han","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068982210","display_name":"Rahul Thomas","orcid":"https://orcid.org/0009-0004-4755-5174"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Thomas","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035065032","display_name":"H.S. Zhang","orcid":"https://orcid.org/0009-0008-2641-5569"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotong Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yi Du","orcid":"https://orcid.org/0009-0006-5218-7665"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Du","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103283238","display_name":"Hansheng Chen","orcid":"https://orcid.org/0000-0002-9294-5970"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hansheng Chen","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073714926","display_name":"Francis Engelmann","orcid":"https://orcid.org/0000-0001-5745-2137"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francis Engelmann","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072580786","display_name":"Suya You","orcid":"https://orcid.org/0000-0002-6387-7024"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suya You","raw_affiliation_strings":["DEVCOM Army Research Laboratory, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065368881","display_name":"Leonidas Guibas","orcid":"https://orcid.org/0000-0002-8315-4886"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonidas Guibas","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100658703"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":3.7474,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9364928,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.7734000086784363,"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":0.7734000086784363,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.049300000071525574,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.02070000022649765,"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/cad","display_name":"CAD","score":0.6883000135421753},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6851999759674072},{"id":"https://openalex.org/keywords/reverse-engineering","display_name":"Reverse engineering","score":0.6025999784469604},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5715000033378601},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4851999878883362},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.35740000009536743},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.34389999508857727},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.32739999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8084999918937683},{"id":"https://openalex.org/C194789388","wikidata":"https://www.wikidata.org/wiki/Q17855283","display_name":"CAD","level":2,"score":0.6883000135421753},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6851999759674072},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.6025999784469604},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49149999022483826},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4851999878883362},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39879998564720154},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3427000045776367},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32739999890327454},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C119823426","wikidata":"https://www.wikidata.org/wiki/Q184793","display_name":"Computer Aided Design","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757377.3763891","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1513343572","display_name":null,"funder_award_id":"Outstanding Doctoral Graduates Development Scholarship","funder_id":"https://openalex.org/F4320322999","funder_display_name":"Shanghai Jiao Tong University"}],"funders":[{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1969014399","https://openalex.org/W2000018820","https://openalex.org/W2014667763","https://openalex.org/W2028541416","https://openalex.org/W2031760064","https://openalex.org/W2052976238","https://openalex.org/W2060206980","https://openalex.org/W2088157800","https://openalex.org/W2108569747","https://openalex.org/W2112825566","https://openalex.org/W2131954959","https://openalex.org/W2161960196","https://openalex.org/W2180058017","https://openalex.org/W2476974423","https://openalex.org/W2557269700","https://openalex.org/W2612843093","https://openalex.org/W2769439829","https://openalex.org/W2782344141","https://openalex.org/W2796576862","https://openalex.org/W2885163231","https://openalex.org/W2901893665","https://openalex.org/W2902691505","https://openalex.org/W2961368225","https://openalex.org/W2962988048","https://openalex.org/W2963369474","https://openalex.org/W2964341242","https://openalex.org/W2972931660","https://openalex.org/W2981010689","https://openalex.org/W2989341556","https://openalex.org/W3035046407","https://openalex.org/W3106872765","https://openalex.org/W3107320589","https://openalex.org/W3108720268","https://openalex.org/W3155736444","https://openalex.org/W3162843412","https://openalex.org/W3173520058","https://openalex.org/W3174904509","https://openalex.org/W3184081648","https://openalex.org/W3185376398","https://openalex.org/W3193629145","https://openalex.org/W3197943946","https://openalex.org/W4232757299","https://openalex.org/W4237303891","https://openalex.org/W4286611065","https://openalex.org/W4294783216","https://openalex.org/W4312843392","https://openalex.org/W4313034350","https://openalex.org/W4321512645","https://openalex.org/W4385328344","https://openalex.org/W4385490339","https://openalex.org/W4386065741","https://openalex.org/W4389539286","https://openalex.org/W4391244152","https://openalex.org/W4400818419","https://openalex.org/W4402727059","https://openalex.org/W4413147004","https://openalex.org/W4413147724","https://openalex.org/W4415797935"],"related_works":[],"abstract_inverted_index":{"Reverse":[0],"engineering":[1,87],"3D":[2],"computer-aided":[3],"design":[4],"(CAD)":[5],"models":[6,43,110],"from":[7,159],"images":[8,73,174],"is":[9],"an":[10,68,152],"important":[11],"task":[12,28,101],"for":[13],"many":[14],"downstream":[15],"applications":[16],"including":[17],"interactive":[18],"editing,":[19],"manufacturing,":[20],"architecture,":[21],"robotics,":[22],"etc.":[23],"The":[24],"difficulty":[25],"of":[26,146,156],"the":[27,35,39,85,100,117,132,138,144,176],"lies":[29],"in":[30,67,175,184],"vast":[31],"representational":[32],"disparities":[33],"between":[34],"CAD":[36,42,154],"output":[37],"and":[38,65,81,166,179],"image":[40],"input.":[41],"are":[44],"precise,":[45],"programmatic":[46],"constructs":[47],"that":[48,97,129],"involves":[49],"sequential":[50],"operations":[51],"combining":[52],"discrete":[53,119,133],"command":[54],"structure":[55,121,134],"with":[56,122,135],"continuous":[57,139],"attributes":[58],"\u2013":[59],"making":[60],"it":[61],"challenging":[62],"to":[63,115],"learn":[64],"optimize":[66],"end-to-end":[69],"fashion.":[70],"Concurrently,":[71],"input":[72],"introduce":[74,93],"inherent":[75],"challenges":[76],"such":[77],"as":[78],"photometric":[79],"variability":[80],"sensor":[82],"noise,":[83],"complicating":[84],"reverse":[86],"process.":[88],"In":[89],"this":[90],"work,":[91],"we":[92,106,126,149],"a":[94,112],"novel":[95],"approach":[96,165],"conditionally":[98],"factorizes":[99],"into":[102],"two":[103],"sub-problems.":[104],"First,":[105],"leverage":[107],"vision-language":[108],"foundation":[109],"(VLMs),":[111],"finetuned":[113],"Llama3.2,":[114],"predict":[116],"global":[118],"base":[120],"semantic":[123],"information.":[124],"Second,":[125],"propose":[127],"TrAssembler":[128],"conditioned":[130],"on":[131],"semantics":[136],"predicts":[137],"attribute":[140],"values.":[141],"To":[142],"support":[143],"training":[145],"our":[147,164],"TrAssembler,":[148],"further":[150],"constructed":[151],"annotated":[153],"dataset":[155],"common":[157],"objects":[158],"ShapeNet.":[160],"Putting":[161],"all":[162],"together,":[163],"data":[167,180],"demonstrate":[168],"significant":[169],"first":[170],"steps":[171],"towards":[172],"CAD-ifying":[173],"wild.":[177],"Code":[178],"can":[181],"be":[182],"found":[183],"https://github.com/qq456cvb/Img2CAD.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-12-08T00:00:00"}