{"id":"https://openalex.org/W7124454695","doi":"https://doi.org/10.1007/s44163-025-00797-6","title":"Generative AI Shanshui animation enhancement using Perlin noise and diffusion models","display_name":"Generative AI Shanshui animation enhancement using Perlin noise and diffusion models","publication_year":2026,"publication_date":"2026-01-16","ids":{"openalex":"https://openalex.org/W7124454695","doi":"https://doi.org/10.1007/s44163-025-00797-6"},"language":"en","primary_location":{"id":"doi:10.1007/s44163-025-00797-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-025-00797-6","pdf_url":null,"source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s44163-025-00797-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069367912","display_name":"Kanoksak Wattanachote","orcid":"https://orcid.org/0000-0001-6558-9395"},"institutions":[{"id":"https://openalex.org/I25399158","display_name":"Mahidol University","ror":"https://ror.org/01znkr924","country_code":"TH","type":"education","lineage":["https://openalex.org/I25399158"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Kanoksak Wattanachote","raw_affiliation_strings":["Faculty of Information and Communication Technology, Mahidol University, Phutthamonthon Sai 4 Rd., Salaya, Nakhon Pathom, 73170, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information and Communication Technology, Mahidol University, Phutthamonthon Sai 4 Rd., Salaya, Nakhon Pathom, 73170, Thailand","institution_ids":["https://openalex.org/I25399158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113690345","display_name":"Chih-Yang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Yang Lin","raw_affiliation_strings":["Department of Mechanical Engineering, National Central University, Zhongda Rd., Zhongli,  Taoyuan, 320317, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, National Central University, Zhongda Rd., Zhongli,  Taoyuan, 320317, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017100735","display_name":"Shao-En Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shao-En Hsu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Zhongda Rd., Zhongli, Taoyuan, 320317, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Zhongda Rd., Zhongli, Taoyuan, 320317, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081089928","display_name":"Timothy K. Shih","orcid":"https://orcid.org/0000-0003-4154-4752"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Timothy K. Shih","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Zhongda Rd., Zhongli, Taoyuan, 320317, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Zhongda Rd., Zhongli, Taoyuan, 320317, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069367912"],"corresponding_institution_ids":["https://openalex.org/I25399158"],"apc_list":{"value":1340,"currency":"USD","value_usd":1340},"apc_paid":{"value":1340,"currency":"USD","value_usd":1340},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06000638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"1","first_page":null,"last_page":null},"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":0.5679000020027161,"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":0.5679000020027161,"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/T12290","display_name":"Human Motion and Animation","score":0.07339999824762344,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.0689999982714653,"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/animation","display_name":"Animation","score":0.6119999885559082},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5526999831199646},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47369998693466187},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.4526999890804291},{"id":"https://openalex.org/keywords/generative-design","display_name":"Generative Design","score":0.42890000343322754},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics","score":0.420199990272522},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41690000891685486},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3991999924182892},{"id":"https://openalex.org/keywords/texture-synthesis","display_name":"Texture synthesis","score":0.38609999418258667},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.38109999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139999866485596},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6119999885559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086999773979187},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5526999831199646},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4560000002384186},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.4526999890804291},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.42890000343322754},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41690000891685486},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3991999924182892},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.38609999418258667},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C170477896","wikidata":"https://www.wikidata.org/wiki/Q17039022","display_name":"Ideation","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.3433000147342682},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.32919999957084656},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C56435381","wikidata":"https://www.wikidata.org/wiki/Q1196371","display_name":"Geometric transformation","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3050000071525574},{"id":"https://openalex.org/C32990609","wikidata":"https://www.wikidata.org/wiki/Q306542","display_name":"Transformation geometry","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C205783811","wikidata":"https://www.wikidata.org/wiki/Q11629","display_name":"Painting","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.27320000529289246},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44163-025-00797-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-025-00797-6","pdf_url":null,"source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:98466d7b1c804b55a194cae91f091ef7","is_oa":true,"landing_page_url":"https://doaj.org/article/98466d7b1c804b55a194cae91f091ef7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Discover Artificial Intelligence, Vol 6, Iss 1 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44163-025-00797-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-025-00797-6","pdf_url":null,"source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4188031256198883,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1535432106","https://openalex.org/W1966832848","https://openalex.org/W2005600574","https://openalex.org/W2106462739","https://openalex.org/W2116331961","https://openalex.org/W2236925012","https://openalex.org/W2604721644","https://openalex.org/W2963184176","https://openalex.org/W3004165104","https://openalex.org/W3011704330","https://openalex.org/W4239515185","https://openalex.org/W4312933868","https://openalex.org/W4383619608","https://openalex.org/W4385412453","https://openalex.org/W4386071778","https://openalex.org/W4386072096","https://openalex.org/W4386362624","https://openalex.org/W4389544144","https://openalex.org/W4390872556","https://openalex.org/W4390873054","https://openalex.org/W4400580599","https://openalex.org/W4407237199","https://openalex.org/W4408709028"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1],"models":[2],"have":[3],"achieved":[4],"remarkable":[5],"advancements":[6],"in":[7,14,121,130,144],"image":[8],"generation":[9,47],"but":[10,147],"face":[11],"persistent":[12],"challenges":[13],"synthesizing":[15],"traditional":[16],"Shanshui":[17,45,89,166],"(mountain-water)":[18],"landscape":[19,46,103],"paintings":[20],"due":[21],"to":[22,43],"limited":[23],"domain-specific":[24],"training":[25],"data":[26],"and":[27,41,48,71,77,95,125,158],"the":[28,85,98,139,153,162],"complexity":[29],"of":[30,87,101,141,155,164],"aesthetic":[31],"principles.":[32],"This":[33,134],"study":[34],"integrated":[35],"Perlin":[36,50],"Noise,":[37],"Stable":[38],"Diffusion,":[39],"ControlNet,":[40],"AnimateDiff":[42,96],"enhance":[44],"animation.":[49,167],"Noise":[51],"constructs":[52],"naturalistic":[53],"skeletal":[54],"structures,":[55],"which":[56],"are":[57],"further":[58],"refined":[59],"using":[60],"ControlNet":[61],"for":[62,152],"precise":[63],"structural":[64],"control.":[65],"Advanced":[66],"prompt":[67,75],"engineering":[68],"with":[69],"GPT-4":[70],"Textual":[72],"Inversion":[73],"improved":[74,84],"descriptiveness":[76],"mitigated":[78],"low-quality":[79],"outputs.":[80],"Furthermore,":[81],"LoRA":[82],"fine-tuning":[83],"adaptability":[86],"our":[88],"landscapes":[90],"model.":[91],"Integrating":[92],"I2V":[93],"Encoders":[94],"enabled":[97],"seamless":[99],"transformation":[100],"static":[102],"images":[104],"into":[105],"dynamic":[106],"animations,":[107],"preserving":[108],"artistic":[109],"authenticity":[110],"while":[111],"introducing":[112],"motion":[113],"consistency.":[114],"The":[115],"experimental":[116],"results":[117],"demonstrated":[118],"significant":[119],"improvements":[120],"realism,":[122],"stylistic":[123],"fidelity,":[124],"diversity,":[126],"addressing":[127],"key":[128],"limitations":[129],"existing":[131],"generative":[132,142],"approaches.":[133],"framework":[135],"not":[136],"only":[137],"advances":[138],"field":[140],"AI":[143],"digital":[145],"art":[146],"also":[148],"offers":[149],"new":[150],"opportunities":[151],"creation":[154],"multimedia":[156],"content":[157],"cultural":[159],"preservation":[160],"through":[161],"synthesis":[163],"computational":[165]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-01-17T00:00:00"}
