{"id":"https://openalex.org/W4407129037","doi":"https://doi.org/10.1109/iccv51701.2025.01835","title":"LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer","display_name":"LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4407129037","doi":"https://doi.org/10.1109/iccv51701.2025.01835"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01835","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.01105","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019405339","display_name":"Yiren Song","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yiren Song","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Danze Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Danze Chen","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mike Zheng Shou","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19731","last_page":"19741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9656999707221985,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9656999707221985,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9535999894142151,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T13382","display_name":"Robotics and Automated Systems","score":0.9340999722480774,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/scalable-vector-graphics","display_name":"Scalable Vector Graphics","score":0.8622754812240601},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48672130703926086},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.43586379289627075},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.43127283453941345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3419768214225769},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.26041847467422485},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11864283680915833},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1066732108592987},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10514217615127563},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05886992812156677},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.058704257011413574}],"concepts":[{"id":"https://openalex.org/C202629362","wikidata":"https://www.wikidata.org/wiki/Q2078","display_name":"Scalable Vector Graphics","level":2,"score":0.8622754812240601},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48672130703926086},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.43586379289627075},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.43127283453941345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3419768214225769},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.26041847467422485},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11864283680915833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1066732108592987},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10514217615127563},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05886992812156677},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.058704257011413574}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01835","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:2502.01105","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01105","pdf_url":"https://arxiv.org/pdf/2502.01105","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.01105","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.01105","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.01105","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01105","pdf_url":"https://arxiv.org/pdf/2502.01105","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2358969090","https://openalex.org/W3183425535","https://openalex.org/W2354624479","https://openalex.org/W2394137533","https://openalex.org/W2362190996","https://openalex.org/W2385461408","https://openalex.org/W2387643967"],"abstract_inverted_index":{"Generating":[0],"cognitive-aligned":[1],"layered":[2,35],"SVGs":[3],"remains":[4],"challenging":[5],"due":[6],"to":[7],"existing":[8],"methods'":[9],"tendencies":[10],"toward":[11],"either":[12],"oversimplified":[13],"single-layer":[14],"outputs":[15],"or":[16],"optimization-induced":[17],"shape":[18],"redundancies.":[19],"We":[20],"propose":[21],"LayerTracer,":[22],"a":[23,40,54,82],"diffusion":[24,84],"transformer":[25],"based":[26],"framework":[27],"that":[28,62,86],"bridges":[29],"this":[30],"gap":[31],"by":[32],"learning":[33],"designers'":[34],"SVG":[36],"creation":[37],"processes":[38],"from":[39],"novel":[41],"dataset":[42],"of":[43],"sequential":[44],"design":[45,65,123],"operations.":[46],"Our":[47],"approach":[48],"operates":[49],"in":[50,111],"two":[51],"phases:":[52],"First,":[53],"text-conditioned":[55],"DiT":[56],"generates":[57],"multi-phase":[58],"rasterized":[59],"construction":[60],"blueprints":[61],"simulate":[63],"human":[64],"workflows.":[66],"Second,":[67],"layer-wise":[68],"vectorization":[69],"with":[70,121],"path":[71],"deduplication":[72],"produces":[73],"clean,":[74],"editable":[75],"SVGs.":[76],"For":[77],"image":[78],"vectorization,":[79],"we":[80],"introduce":[81],"conditional":[83],"mechanism":[85],"encodes":[87],"reference":[88],"images":[89],"into":[90],"latent":[91],"tokens,":[92],"guiding":[93],"hierarchical":[94],"reconstruction":[95],"while":[96],"preserving":[97],"structural":[98],"integrity.":[99],"Extensive":[100],"experiments":[101],"demonstrate":[102],"LayerTracer's":[103],"superior":[104],"performance":[105],"against":[106],"optimization-based":[107],"and":[108,115],"neural":[109],"baselines":[110],"both":[112],"generation":[113],"quality":[114],"editability,":[116],"effectively":[117],"aligning":[118],"AI-generated":[119],"vectors":[120],"professional":[122],"cognition.":[124]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}