{"id":"https://openalex.org/W4403333950","doi":"https://doi.org/10.1145/3654777.3676444","title":"Block and Detail: Scaffolding Sketch-to-Image Generation","display_name":"Block and Detail: Scaffolding Sketch-to-Image Generation","publication_year":2024,"publication_date":"2024-10-11","ids":{"openalex":"https://openalex.org/W4403333950","doi":"https://doi.org/10.1145/3654777.3676444"},"language":"en","primary_location":{"id":"doi:10.1145/3654777.3676444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3654777.3676444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"type":"conference-paper","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/A5069897950","display_name":"Vishnu Sarukkai","orcid":"https://orcid.org/0009-0006-9809-9994"},"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":"Vishnu Sarukkai","raw_affiliation_strings":["Computer Science, Stanford University, United States"],"raw_orcid":"https://orcid.org/0009-0006-9809-9994","affiliations":[{"raw_affiliation_string":"Computer Science, Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100578101","display_name":"Lu Yuan","orcid":"https://orcid.org/0009-0004-6399-4337"},"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":"Lu Yuan","raw_affiliation_strings":["Stanford University, United States"],"raw_orcid":"https://orcid.org/0009-0004-6399-4337","affiliations":[{"raw_affiliation_string":"Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107990963","display_name":"Mia Tang","orcid":"https://orcid.org/0009-0009-3553-3732"},"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":"Mia Tang","raw_affiliation_strings":["Stanford University, United States"],"raw_orcid":"https://orcid.org/0009-0009-3553-3732","affiliations":[{"raw_affiliation_string":"Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045835385","display_name":"Maneesh Agrawala","orcid":"https://orcid.org/0000-0002-8996-7327"},"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":"Maneesh Agrawala","raw_affiliation_strings":["Stanford University, United States and Roblox, United States"],"raw_orcid":"https://orcid.org/0000-0002-8996-7327","affiliations":[{"raw_affiliation_string":"Stanford University, United States and Roblox, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037444018","display_name":"Kayvon Fatahalian","orcid":"https://orcid.org/0000-0001-8754-0429"},"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":"Kayvon Fatahalian","raw_affiliation_strings":["Stanford University, United States"],"raw_orcid":"https://orcid.org/0000-0001-8754-0429","affiliations":[{"raw_affiliation_string":"Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":3.8128,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.95712909,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9944999814033508,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9805999994277954,"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/sketch","display_name":"Sketch","score":0.7271376252174377},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6544460654258728},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6390827894210815},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5108363628387451},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3236405849456787},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19314515590667725},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12511911988258362},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06794467568397522}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.7271376252174377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6544460654258728},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6390827894210815},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5108363628387451},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3236405849456787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19314515590667725},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12511911988258362},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06794467568397522}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3654777.3676444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3654777.3676444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W591589697","https://openalex.org/W1583837637","https://openalex.org/W1982877658","https://openalex.org/W2026996548","https://openalex.org/W2135248415","https://openalex.org/W2168653519","https://openalex.org/W2337562199","https://openalex.org/W2406512702","https://openalex.org/W2908869154","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963561004","https://openalex.org/W2965128575","https://openalex.org/W3175344711","https://openalex.org/W3185618248","https://openalex.org/W4247620880","https://openalex.org/W4255447789","https://openalex.org/W4312933868","https://openalex.org/W4313059227","https://openalex.org/W4319301041","https://openalex.org/W4385271281","https://openalex.org/W4385537492","https://openalex.org/W4387969545","https://openalex.org/W4390873054","https://openalex.org/W4394596511"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W2591066345"],"abstract_inverted_index":{"We":[0,40,94,126,176],"introduce":[1],"a":[2,42,65,97,106,142,184,208],"novel":[3],"sketch-to-image":[4],"tool":[5,16],"that":[6,71,111,128,139,157,196],"aligns":[7],"with":[8,183],"the":[9,25,56,60,75,82,160,163,174,178,200,215,227],"iterative":[10,57],"refinement":[11],"process":[12],"of":[13,29,145,167,180,186,202,214,226],"artists.":[14],"Our":[15],"lets":[17],"users":[18],"sketch":[19],"blocking":[20,92],"strokes":[21,33,76,115],"to":[22,34,67,104,116,173],"coarsely":[23],"represent":[24],"placement":[26],"and":[27,31,38,78,80,165,188,217],"form":[28],"objects":[30,168],"detail":[32],"refine":[35],"their":[36],"shape":[37,164],"silhouettes.":[39],"develop":[41],"two-pass":[43],"algorithm":[44,206],"for":[45,212],"generating":[46],"high-fidelity":[47,148],"images":[48,149,203,220],"from":[49,136,204],"such":[50],"sketches":[51,138],"at":[52],"any":[53],"point":[54],"in":[55,81,224],"process.":[58],"In":[59],"first":[61],"pass":[62,84],"we":[63,85],"use":[64],"ControlNet":[66,107,131,211],"generate":[68,133],"an":[69],"image":[70],"strictly":[72],"follows":[73],"all":[74],"(blocking":[77],"detail)":[79],"second":[83],"add":[86,170],"variation":[87],"by":[88,151],"renoising":[89],"regions":[90,110,121],"surrounding":[91],"strokes.":[93,146],"also":[95],"present":[96],"dataset":[98],"generation":[99],"scheme":[100],"that,":[101],"when":[102],"used":[103],"train":[105],"architecture,":[108],"allows":[109],"do":[112],"not":[113],"contain":[114,141],"be":[117],"interpreted":[118],"as":[119,155],"not-yet-specified":[120],"rather":[122],"than":[123],"empty":[124],"space.":[125],"show":[127],"this":[129],"partial-sketch-aware":[130],"can":[132,158],"coherent":[134],"elements":[135,172],"partial":[137],"only":[140],"small":[143],"number":[144],"The":[147],"produced":[150],"our":[152,181,205,219],"approach":[153,182],"serve":[154],"scaffolds":[156],"help":[159],"user":[161,193],"adjust":[162],"proportions":[166],"or":[169],"additional":[171],"composition.":[175],"demonstrate":[177],"effectiveness":[179],"variety":[185],"examples":[187],"evaluative":[189,192],"comparisons.":[190],"Quantitatively,":[191],"feedback":[194],"indicates":[195],"novice":[197],"viewers":[198],"prefer":[199],"quality":[201],"over":[207],"baseline":[209],"Scribble":[210],"84%":[213],"pairs":[216],"found":[218],"had":[221],"less":[222],"distortion":[223],"81%":[225],"pairs.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}