{"id":"https://openalex.org/W4416214873","doi":"https://doi.org/10.1109/tmm.2025.3632651","title":"MDT-FI: Mask-Guided Dual-Branch Transformer With Texture and Structure Feature Interaction for Image Inpainting","display_name":"MDT-FI: Mask-Guided Dual-Branch Transformer With Texture and Structure Feature Interaction for Image Inpainting","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416214873","doi":"https://doi.org/10.1109/tmm.2025.3632651"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3632651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632651","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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":"https://openalex.org/A5092229448","display_name":"Dong Liu","orcid":"https://orcid.org/0009-0006-3663-9254"},"institutions":[{"id":"https://openalex.org/I4210131919","display_name":"Xi'an University of Technology","ror":"https://ror.org/038avdt50","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131919"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Liu","raw_affiliation_strings":["Department of Mathematics, Xi'an University of Technology, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0006-3663-9254","affiliations":[{"raw_affiliation_string":"Department of Mathematics, Xi'an University of Technology, Xi'an, China","institution_ids":["https://openalex.org/I4210131919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029247516","display_name":"Xiaofeng Wang","orcid":"https://orcid.org/0000-0002-0861-8193"},"institutions":[{"id":"https://openalex.org/I4210131919","display_name":"Xi'an University of Technology","ror":"https://ror.org/038avdt50","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131919"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Wang","raw_affiliation_strings":["Department of Mathematics, Xi'an University of Technology, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-0861-8193","affiliations":[{"raw_affiliation_string":"Department of Mathematics, Xi'an University of Technology, Xi'an, China","institution_ids":["https://openalex.org/I4210131919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076278720","display_name":"Ruidong Han","orcid":"https://orcid.org/0000-0002-4630-3731"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruidong Han","raw_affiliation_strings":["School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-4630-3731","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianghua Li","orcid":"https://orcid.org/0000-0002-6443-1382"},"institutions":[{"id":"https://openalex.org/I4210131919","display_name":"Xi'an University of Technology","ror":"https://ror.org/038avdt50","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131919"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianghua Li","raw_affiliation_strings":["Department of Mathematics, Xi'an University of Technology, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-6443-1382","affiliations":[{"raw_affiliation_string":"Department of Mathematics, Xi'an University of Technology, Xi'an, China","institution_ids":["https://openalex.org/I4210131919"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006557413","display_name":"Shanmin Pang","orcid":"https://orcid.org/0000-0001-7217-864X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanmin Pang","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-7217-864X","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092229448"],"corresponding_institution_ids":["https://openalex.org/I4210131919"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3294665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"985","last_page":"997"},"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":0.9416000247001648,"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":0.9416000247001648,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.008100000210106373,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T11448","display_name":"Face recognition and analysis","score":0.005799999926239252,"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/inpainting","display_name":"Inpainting","score":0.7371000051498413},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5645999908447266},{"id":"https://openalex.org/keywords/texture-synthesis","display_name":"Texture synthesis","score":0.49399998784065247},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4447999894618988},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4120999872684479},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.40450000762939453},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4041000008583069},{"id":"https://openalex.org/keywords/image-texture","display_name":"Image texture","score":0.3813000023365021},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.37040001153945923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8306999802589417},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.7371000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7297999858856201},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5645999908447266},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.529699981212616},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.49399998784065247},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.40450000762939453},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.3813000023365021},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C200873422","wikidata":"https://www.wikidata.org/wiki/Q5448821","display_name":"Filling-in","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3522000014781952},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2964000105857849},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3632651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632651","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1975049209","https://openalex.org/W2055132753","https://openalex.org/W2133665775","https://openalex.org/W2137560623","https://openalex.org/W2295936755","https://openalex.org/W2557414982","https://openalex.org/W2732026016","https://openalex.org/W2738588019","https://openalex.org/W2798365772","https://openalex.org/W2962785568","https://openalex.org/W2963270367","https://openalex.org/W2963420272","https://openalex.org/W2982763192","https://openalex.org/W2989207674","https://openalex.org/W2991377405","https://openalex.org/W2998075999","https://openalex.org/W3001217199","https://openalex.org/W3035002246","https://openalex.org/W3035426499","https://openalex.org/W3035512475","https://openalex.org/W3043547428","https://openalex.org/W3108554146","https://openalex.org/W3112341889","https://openalex.org/W3135339232","https://openalex.org/W3174754903","https://openalex.org/W3192575616","https://openalex.org/W3195697494","https://openalex.org/W3199003182","https://openalex.org/W3203538104","https://openalex.org/W3204170321","https://openalex.org/W4226300688","https://openalex.org/W4285160254","https://openalex.org/W4285215683","https://openalex.org/W4289752563","https://openalex.org/W4290860662","https://openalex.org/W4304014657","https://openalex.org/W4312238440","https://openalex.org/W4312383858","https://openalex.org/W4312444052","https://openalex.org/W4312771828","https://openalex.org/W4313154016","https://openalex.org/W4319300595","https://openalex.org/W4378364836","https://openalex.org/W4385245566","https://openalex.org/W4386158379","https://openalex.org/W4390874159","https://openalex.org/W4390954029","https://openalex.org/W4392405703","https://openalex.org/W4392693662","https://openalex.org/W4393148515","https://openalex.org/W4399565315","https://openalex.org/W4403116532"],"related_works":[],"abstract_inverted_index":{"Image":[0],"inpainting":[1],"has":[2],"attracted":[3],"considerable":[4],"attention":[5,123],"in":[6,36,168],"computer":[7],"vision":[8],"and":[9,41,54,80,105,120,137,166,177],"image":[10],"processing":[11],"due":[12],"to":[13,125,159],"its":[14],"wide":[15],"range":[16],"of":[17,39,58,91,163],"applications.":[18],"While":[19],"deep":[20],"learning-based":[21],"methods":[22,47],"have":[23],"shown":[24],"promising":[25],"potential,":[26],"accurately":[27],"recovering":[28],"pixel-level":[29],"details":[30],"remains":[31],"a":[32,55,67,121,154],"significant":[33],"challenge,":[34],"particularly":[35],"the":[37,95,100,106,161,169],"presence":[38],"large":[40],"irregular":[42],"missing":[43],"regions.":[44],"Furthermore,":[45],"existing":[46],"are":[48],"limited":[49],"by":[50,84],"unidirectional":[51],"semantic":[52],"guidance":[53],"localized":[56],"understanding":[57],"global":[59,81,146],"structural":[60,147],"context.":[61],"In":[62],"this":[63],"study,":[64],"we":[65],"propose":[66],"mask-guided":[68,122],"dual-branch":[69],"Transformer-based":[70],"framework,":[71],"named":[72],"MDT-FI,":[73],"which":[74],"effectively":[75],"balances":[76],"local":[77,141],"detail":[78],"restoration":[79],"contextual":[82],"reasoning":[83],"explicitly":[85],"modeling":[86],"long-range":[87],"dependencies.":[88],"MDT-FI":[89,183],"consists":[90],"three":[92],"key":[93],"components:":[94],"Interactive":[96],"Attention":[97],"Module":[98,103],"(IAM),":[99],"Spectral":[101],"Harmonization":[102],"(SHM),":[104],"Lateral":[107],"Adaptation":[108],"Network":[109],"(LAN).":[110],"The":[111],"model":[112],"integrates":[113],"multi-scale":[114],"feature":[115,129,155],"interaction,":[116],"frequency-domain":[117],"information":[118],"fusion,":[119],"mechanism":[124],"progressively":[126],"build":[127],"cross-level":[128],"associations.":[130],"This":[131],"design":[132],"facilitates":[133],"multi-level":[134],"representation":[135],"learning":[136],"optimization,":[138],"thereby":[139],"enhancing":[140],"texture":[142,165],"synthesis":[143],"while":[144],"preserving":[145],"consistency.":[148],"To":[149],"further":[150],"improve":[151],"perceptual":[152],"quality,":[153],"augmenter":[156],"is":[157],"employed":[158],"assess":[160],"fidelity":[162],"both":[164],"structure":[167],"generated":[170],"results.":[171],"Extensive":[172],"experiments":[173],"on":[174],"CelebA-HQ,":[175],"Places2,":[176],"Paris":[178],"Street":[179],"View":[180],"demonstrate":[181],"that":[182],"significantly":[184],"outperforms":[185],"state-of-the-art":[186],"methods.":[187]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-14T00:00:00"}