{"id":"https://openalex.org/W4415539475","doi":"https://doi.org/10.1145/3746027.3755174","title":"CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation","display_name":"CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539475","doi":"https://doi.org/10.1145/3746027.3755174"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755174","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.03540","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111102145","display_name":"Ruoxuan Zhang","orcid":"https://orcid.org/0009-0002-0829-6267"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoxuan Zhang","raw_affiliation_strings":["Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0009-0002-0829-6267","affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001013820","display_name":"Bin Wen","orcid":"https://orcid.org/0009-0000-4665-6978"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wen","raw_affiliation_strings":["Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0009-0000-4665-6978","affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013026466","display_name":"Hongxia Xie","orcid":"https://orcid.org/0000-0002-5652-4327"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxia Xie","raw_affiliation_strings":["Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0002-5652-4327","affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101158022","display_name":"Yi Yao","orcid":"https://orcid.org/0000-0001-8227-5662"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi Yao","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-8227-5662","affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120132100","display_name":"Songhan Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songhan Zuo","raw_affiliation_strings":["Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0009-0006-5178-752X","affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016296062","display_name":"Jian-Yu Jiang-Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jian-Yu Jiang-Lin","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0005-5739-4228","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040050806","display_name":"Hong-Han Shuai","orcid":"https://orcid.org/0000-0003-2216-077X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hong-Han Shuai","raw_affiliation_strings":["National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-2216-077X","affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000780442","display_name":"Wen-Huang Cheng","orcid":"https://orcid.org/0000-0002-4662-7875"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Huang Cheng","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-4662-7875","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"7854","last_page":"7863"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9969000220298767,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9926999807357788,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9919000267982483,"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/recipe","display_name":"Recipe","score":0.9764000177383423},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6481999754905701},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6035000085830688},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5561000108718872},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43779999017715454},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4302000105381012},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42879998683929443},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3808000087738037},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.3515999913215637}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.9764000177383423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429999709129333},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6481999754905701},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6035000085830688},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5561000108718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5277000069618225},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40400001406669617},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.3515999913215637},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3465000092983246},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30000001192092896},{"id":"https://openalex.org/C2985909886","wikidata":"https://www.wikidata.org/wiki/Q193147","display_name":"Spatial coherence","level":3,"score":0.29580000042915344},{"id":"https://openalex.org/C113230428","wikidata":"https://www.wikidata.org/wiki/Q7247149","display_name":"Procedural modeling","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.2583000063896179},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755174","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.03540","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.03540","pdf_url":"https://arxiv.org/pdf/2512.03540","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":"pmh:oai:arXiv.org:2512.03540","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.03540","pdf_url":"https://arxiv.org/pdf/2512.03540","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1635450702","display_name":null,"funder_award_id":"62406126","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2526198870","https://openalex.org/W2952132648","https://openalex.org/W2960416371","https://openalex.org/W2966316879","https://openalex.org/W3009381623","https://openalex.org/W3081217025","https://openalex.org/W3093100367","https://openalex.org/W3093234244","https://openalex.org/W3159481202","https://openalex.org/W3170706004","https://openalex.org/W3207251446","https://openalex.org/W4291433229","https://openalex.org/W4304014246","https://openalex.org/W4312697499","https://openalex.org/W4312933868","https://openalex.org/W4319996536","https://openalex.org/W4386076027","https://openalex.org/W4388187930","https://openalex.org/W4390872297","https://openalex.org/W4393200103","https://openalex.org/W4402724515","https://openalex.org/W4403791449","https://openalex.org/W4403792157"],"related_works":[],"abstract_inverted_index":{"Cooking":[0],"is":[1],"a":[2,62,80,120,127],"sequential":[3],"and":[4,21,82,137,140,169,184,194],"visually":[5],"grounded":[6],"activity,":[7],"where":[8],"each":[9],"step":[10],"such":[11],"as":[12],"chopping,":[13],"mixing,":[14],"or":[15],"frying":[16],"carries":[17],"both":[18,134],"procedural":[19,195],"logic":[20],"visual":[22,178],"semantics.":[23],"While":[24],"recent":[25],"diffusion":[26],"models":[27],"have":[28],"shown":[29],"strong":[30],"capabilities":[31],"in":[32,58,167,191],"text-to-image":[33],"generation,":[34],"they":[35],"struggle":[36],"to":[37,52,54],"handle":[38],"structured":[39],"multi-step":[40,182],"scenarios":[41],"like":[42],"recipe":[43,47,59,156],"illustration.":[44],"Additionally,":[45],"current":[46],"illustration":[48,157],"methods":[49,166],"are":[50,200],"unable":[51],"adjust":[53],"the":[55,69],"natural":[56],"variability":[57],"length,":[60],"generating":[61],"fixed":[63],"number":[64],"of":[65,68,97,180],"images":[66],"regardless":[67],"actual":[70],"instructions":[71,96,183],"structure.":[72],"To":[73],"address":[74],"these":[75],"limitations,":[76],"we":[77],"present":[78],"CookAnything,":[79],"flexible":[81],"consistent":[83],"diffusion-based":[84],"framework":[85,101,174],"that":[86,132,160],"generates":[87],"coherent,":[88],"semantically":[89],"distinct":[90],"image":[91,117],"sequences":[92],"from":[93],"textual":[94,113],"cooking":[95],"arbitrary":[98],"length.":[99],"The":[100,172],"introduces":[102],"three":[103],"key":[104],"components:":[105],"(1)":[106],"Step-wise":[107],"Regional":[108],"Control":[109,144],"(SRC),":[110],"which":[111,146],"aligns":[112],"steps":[114],"with":[115],"corresponding":[116],"regions":[118],"within":[119],"single":[121],"denoising":[122],"process;":[123],"(2)":[124],"Flexible":[125],"RoPE,":[126],"step-aware":[128],"positional":[129],"encoding":[130],"mechanism":[131],"enhances":[133],"temporal":[135],"coherence":[136],"spatial":[138],"diversity;":[139],"(3)":[141],"Cross-Step":[142],"Consistency":[143],"(CSCC),":[145],"maintains":[147],"fine-grained":[148],"ingredient":[149],"consistency":[150],"across":[151],"steps.":[152],"Experimental":[153],"results":[154],"on":[155],"benchmarks":[158],"show":[159],"CookAnything":[161],"performs":[162],"better":[163],"than":[164],"existing":[165],"training-based":[168],"training-free":[170],"settings.":[171],"proposed":[173],"supports":[175],"scalable,":[176],"high-quality":[177],"synthesis":[179],"complex":[181],"holds":[185],"significant":[186],"potential":[187],"for":[188],"broad":[189],"applications":[190],"instructional":[192],"media,":[193],"content":[196],"creation.":[197],"More":[198],"details":[199],"at":[201],"https://github.com/zhangdaxia22/CookAnything.":[202]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
