{"id":"https://openalex.org/W4415707508","doi":"https://doi.org/10.1109/tcsvt.2025.3626857","title":"Draw Like an Artist: Complex Scene Generation With Diffusion Model via Composition, Painting, and Retouching","display_name":"Draw Like an Artist: Complex Scene Generation With Diffusion Model via Composition, Painting, and Retouching","publication_year":2025,"publication_date":"2025-10-30","ids":{"openalex":"https://openalex.org/W4415707508","doi":"https://doi.org/10.1109/tcsvt.2025.3626857"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3626857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3626857","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Minghao Liu","orcid":"https://orcid.org/0009-0004-1660-9379"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghao Liu","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-1660-9379","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104254027","display_name":"Le Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Zhang","raw_affiliation_strings":["MT Lab, Meitu Inc., Beijing, China","MT Lab of Meitu.Inc, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-1556-8165","affiliations":[{"raw_affiliation_string":"MT Lab, Meitu Inc., Beijing, China","institution_ids":[]},{"raw_affiliation_string":"MT Lab of Meitu.Inc, Beijing, China","institution_ids":["https://openalex.org/I4210152823"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032861309","display_name":"Yingjie Tian","orcid":"https://orcid.org/0000-0002-4675-0398"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjie Tian","raw_affiliation_strings":["School of Economics and Management, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4675-0398","affiliations":[{"raw_affiliation_string":"School of Economics and Management, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101824646","display_name":"Xiaochao Qu","orcid":"https://orcid.org/0000-0002-3181-3704"},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochao Qu","raw_affiliation_strings":["MT Lab, Meitu Inc., Beijing, China","MT Lab of Meitu.Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MT Lab, Meitu Inc., Beijing, China","institution_ids":[]},{"raw_affiliation_string":"MT Lab of Meitu.Inc, Beijing, China","institution_ids":["https://openalex.org/I4210152823"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022372381","display_name":"Luoqi Liu","orcid":"https://orcid.org/0009-0002-6607-4072"},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luoqi Liu","raw_affiliation_strings":["MT Lab, Meitu Inc., Beijing, China","MT Lab of Meitu.Inc, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6607-4072","affiliations":[{"raw_affiliation_string":"MT Lab, Meitu Inc., Beijing, China","institution_ids":[]},{"raw_affiliation_string":"MT Lab of Meitu.Inc, Beijing, China","institution_ids":["https://openalex.org/I4210152823"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ting Liu","orcid":"https://orcid.org/0009-0008-7988-5935"},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["MT Lab, Meitu Inc., Beijing, China","MT Lab of Meitu.Inc, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-7988-5935","affiliations":[{"raw_affiliation_string":"MT Lab, Meitu Inc., Beijing, China","institution_ids":[]},{"raw_affiliation_string":"MT Lab of Meitu.Inc, Beijing, China","institution_ids":["https://openalex.org/I4210152823"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2780937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"4","first_page":"4492","last_page":"4504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9214000105857849,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9214000105857849,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.027499999850988388,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.008299999870359898,"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/set","display_name":"Set (abstract data type)","score":0.6064000129699707},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5763000249862671},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5314000248908997},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4302000105381012},{"id":"https://openalex.org/keywords/painting","display_name":"Painting","score":0.42329999804496765},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.38510000705718994},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3765000104904175},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.36660000681877136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7965999841690063},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6064000129699707},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5763000249862671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5680999755859375},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5331000089645386},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.46650001406669617},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C205783811","wikidata":"https://www.wikidata.org/wiki/Q11629","display_name":"Painting","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.32580000162124634},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3626857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3626857","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,10],"text-to-image":[3],"diffusion":[4,68],"models":[5,95],"have":[6],"demonstrated":[7],"impressive":[8],"capabilities":[9,91],"image":[11,146],"quality.":[12],"However,":[13],"complex":[14,43,99,127,176],"scene":[15,128],"generation":[16,166],"remains":[17,28],"relatively":[18],"unexplored,":[19],"and":[20,45,83,104,108,171],"even":[21,178],"the":[22,60,76,88,126,133,137,145,150,165],"definition":[23,41],"of":[24,42,49,92,136,167],"\u2018complex":[25],"scene\u2019":[26],"itself":[27],"unclear.":[29],"In":[30],"this":[31,35,56],"paper,":[32],"we":[33,64,131],"address":[34],"gap":[36],"by":[37,59],"providing":[38],"a":[39,47,66,140],"precise":[40],"scenes":[44],"introducing":[46],"set":[48],"Complex":[50,71],"Decomposition":[51],"Criteria":[52],"(CDC)":[53],"based":[54,101],"on":[55,102],"definition.":[57],"Inspired":[58],"artist\u2019s":[61],"painting":[62,82],"process,":[63],"propose":[65],"training-free":[67],"framework":[69],"called":[70],"Diffusion":[72],"(CxD),":[73],"which":[74],"divides":[75],"process":[77],"into":[78,139],"three":[79],"stages:":[80],"composition,":[81],"retouching.":[84],"Our":[85],"method":[86,116,158],"leverages":[87],"powerful":[89],"chain-of-thought":[90],"large":[93],"language":[94],"(LLMs)":[96],"to":[97,105,121,124,143],"decompose":[98],"prompts":[100,120],"CDC":[103],"manage":[106],"composition":[107],"layout.":[109],"We":[110],"then":[111],"develop":[112],"an":[113],"attention":[114],"modulation":[115],"that":[117,156],"guides":[118],"simple":[119],"specific":[122],"regions":[123],"complete":[125],"painting.":[129],"Finally,":[130],"inject":[132],"detailed":[134],"output":[135],"LLM":[138],"retouching":[141,151],"model":[142],"enhance":[144],"details,":[147],"thus":[148],"implementing":[149],"stage.":[152],"Extensive":[153],"experiments":[154],"demonstrate":[155],"our":[157],"outperforms":[159],"previous":[160],"SOTA":[161],"approaches,":[162],"significantly":[163],"improving":[164],"high-quality,":[168],"semantically":[169],"consistent,":[170],"visually":[172],"diverse":[173],"images":[174],"for":[175],"scenes,":[177],"with":[179],"intricate":[180],"prompts.":[181]},"counts_by_year":[],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2025-10-30T00:00:00"}