{"id":"https://openalex.org/W7161238643","doi":"https://doi.org/10.1145/3799902.3811174","title":"Img2CADSeq: Image-to-CAD Generation via Sequence-Based Diffusion","display_name":"Img2CADSeq: Image-to-CAD Generation via Sequence-Based Diffusion","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7161238643","doi":"https://doi.org/10.1145/3799902.3811174"},"language":null,"primary_location":{"id":"doi:10.1145/3799902.3811174","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811174","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 Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799902.3811174","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136155902","display_name":"Shiyu Tan","orcid":null},"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":"Shiyu Tan","raw_affiliation_strings":["School of Software and BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-8523-5606","affiliations":[{"raw_affiliation_string":"School of Software and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101737194","display_name":"Zixuan Zhao","orcid":"https://orcid.org/0000-0001-6934-0765"},"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":"Zixuan Zhao","raw_affiliation_strings":["School of Software and BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-3372-4242","affiliations":[{"raw_affiliation_string":"School of Software and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136195644","display_name":"Hao Gao","orcid":null},"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":"Hao Gao","raw_affiliation_strings":["School of Software and BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-5340-2714","affiliations":[{"raw_affiliation_string":"School of Software and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136237723","display_name":"Zhiheng Chen","orcid":null},"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":"Zhiheng Chen","raw_affiliation_strings":["School of Software and BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-6804-294X","affiliations":[{"raw_affiliation_string":"School of Software and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136234077","display_name":"Xiaolong Yin","orcid":null},"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":"Xiaolong Yin","raw_affiliation_strings":["School of Software and BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-2199-0932","affiliations":[{"raw_affiliation_string":"School of Software and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136222653","display_name":"Enya Shen","orcid":null},"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":"Enya Shen","raw_affiliation_strings":["School of Software and BNRist, Tsinghua University, Beijing, China and Haihe Lab of ITAI, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9303-969X","affiliations":[{"raw_affiliation_string":"School of Software and BNRist, Tsinghua University, Beijing, China and Haihe Lab of ITAI, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.8751999735832214,"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":0.8751999735832214,"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":0.03280000016093254,"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/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.008899999782443047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cad","display_name":"CAD","score":0.7275999784469604},{"id":"https://openalex.org/keywords/boundary-representation","display_name":"Boundary representation","score":0.5788999795913696},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5601999759674072},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.535099983215332},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.48809999227523804},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46810001134872437},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.43540000915527344},{"id":"https://openalex.org/keywords/topological-data-analysis","display_name":"Topological data analysis","score":0.41659998893737793}],"concepts":[{"id":"https://openalex.org/C194789388","wikidata":"https://www.wikidata.org/wiki/Q17855283","display_name":"CAD","level":2,"score":0.7275999784469604},{"id":"https://openalex.org/C117258860","wikidata":"https://www.wikidata.org/wiki/Q895153","display_name":"Boundary representation","level":3,"score":0.5788999795913696},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5601999759674072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5485000014305115},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46810001134872437},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C2776477805","wikidata":"https://www.wikidata.org/wiki/Q4460773","display_name":"Topological data analysis","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4115999937057495},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4000999927520752},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C2874115","wikidata":"https://www.wikidata.org/wiki/Q17099562","display_name":"Persistent homology","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C119823426","wikidata":"https://www.wikidata.org/wiki/Q184793","display_name":"Computer Aided Design","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29159998893737793},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2768000066280365},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C92548554","wikidata":"https://www.wikidata.org/wiki/Q2262868","display_name":"Domain model","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25859999656677246}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3799902.3811174","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811174","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 Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.13293","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.13293","pdf_url":"https://arxiv.org/pdf/2605.13293","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"}],"best_oa_location":{"id":"doi:10.1145/3799902.3811174","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811174","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 Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5128108263015747,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Boundary":[0],"Representation":[1],"(BRep)":[2],"is":[3],"the":[4,22,71],"standard":[5,122],"format":[6],"for":[7,137],"Computer-Aided":[8],"Design":[9],"(CAD),":[10],"yet":[11],"reconstructing":[12],"high-quality":[13],"BReps":[14],"from":[15],"single-view":[16],"images":[17],"remains":[18],"challenging":[19],"due":[20],"to":[21,92],"complexity":[23],"of":[24],"topological":[25],"constraints":[26],"and":[27,102,135],"operation":[28],"sequences.":[29],"We":[30],"present":[31],"Img2CADSeq,":[32],"a":[33,45,64,76,94],"multi-stage":[34],"pipeline":[35],"that":[36,115,125],"overcomes":[37],"these":[38],"limitations":[39],"by":[40,50,98],"encoding":[41],"CAD":[42,87,132],"sequences":[43,62,88],"into":[44,63],"three-level":[46],"hierarchical":[47],"codebook.":[48],"Guided":[49],"an":[51],"importance":[52],"prioritization,":[53],"this":[54,138],"strategy":[55],"values":[56],"profiles":[57],"over":[58],"details,":[59],"compressing":[60],"long":[61],"stable":[65],"discrete":[66],"latent":[67],"space.":[68],"To":[69],"bridge":[70],"modality":[72],"gap,":[73],"we":[74],"leverage":[75],"coarse-to-fine":[77],"point":[78],"cloud":[79],"intermediate,":[80],"aligning":[81],"2D":[82],"visual":[83],"features":[84],"with":[85],"3D":[86],"via":[89],"contrastive":[90],"learning":[91],"condition":[93],"VQ-Diffusion":[95],"model.":[96],"Supported":[97],"newly":[99],"introduced":[100],"CAD-220K":[101],"PrintCAD":[103],"datasets,":[104],"our":[105],"approach":[106],"ensures":[107],"robust":[108],"industrial":[109],"domain":[110],"adaptation.":[111],"Extensive":[112],"experiments":[113],"demonstrate":[114],"Img2CADSeq":[116],"significantly":[117],"outperforms":[118],"state-of-the-art":[119],"methods,":[120],"producing":[121],"STEP":[123],"files":[124],"can":[126],"be":[127],"directly":[128],"used":[129],"in":[130],"commercial":[131],"software.":[133],"Code":[134],"data":[136],"paper":[139],"are":[140],"at":[141],"https://github.com/Rilpraa0110/Img2CADSeq":[142]},"counts_by_year":[],"updated_date":"2026-07-17T05:58:32.477365","created_date":"2026-05-16T00:00:00"}