{"id":"https://openalex.org/W4413392204","doi":"https://doi.org/10.1109/tcsvt.2025.3601213","title":"Prompts Libra: Enhanced Image Outpainting Diffusion Model With Balanced Bimodal Guidance","display_name":"Prompts Libra: Enhanced Image Outpainting Diffusion Model With Balanced Bimodal Guidance","publication_year":2025,"publication_date":"2025-08-21","ids":{"openalex":"https://openalex.org/W4413392204","doi":"https://doi.org/10.1109/tcsvt.2025.3601213"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3601213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3601213","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":"https://openalex.org/A5045475334","display_name":"Zongyan Zhang","orcid":"https://orcid.org/0009-0000-5132-3326"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zongyan Zhang","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","School of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643265","display_name":"C. L. Philip Chen","orcid":"https://orcid.org/0000-0001-5451-7230"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"C. L. Philip Chen","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","School of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077816602","display_name":"Zepeng Su","orcid":"https://orcid.org/0000-0001-7691-7075"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zepeng Su","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","School of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378800","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-7025-6365"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","School of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045475334"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19992687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"2","first_page":"1977","last_page":"1992"},"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":0.9855999946594238,"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":0.9855999946594238,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.978600025177002,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.968500018119812,"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/computer-science","display_name":"Computer science","score":0.6167791485786438},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4829908609390259},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45754170417785645},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.42326128482818604},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.405240923166275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3851698040962219},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.33812087774276733},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3323933780193329},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1735854148864746}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6167791485786438},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4829908609390259},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45754170417785645},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.42326128482818604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.405240923166275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3851698040962219},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33812087774276733},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3323933780193329},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1735854148864746},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3601213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3601213","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":[{"id":"https://openalex.org/G1487701234","display_name":null,"funder_award_id":"62222603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4636517650","display_name":null,"funder_award_id":"2024A04J6310","funder_id":"https://openalex.org/F4320336618","funder_display_name":"Science and Technology Program of Suzhou"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336618","display_name":"Science and Technology Program of Suzhou","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1562968274","https://openalex.org/W1861492603","https://openalex.org/W2093422746","https://openalex.org/W2106477124","https://openalex.org/W2131585809","https://openalex.org/W2160526525","https://openalex.org/W2339170012","https://openalex.org/W2732026016","https://openalex.org/W2901084129","https://openalex.org/W2948627722","https://openalex.org/W2981828483","https://openalex.org/W3035251567","https://openalex.org/W3040932449","https://openalex.org/W3091119272","https://openalex.org/W3118896137","https://openalex.org/W3120472021","https://openalex.org/W3180355996","https://openalex.org/W3202296139","https://openalex.org/W3212516020","https://openalex.org/W4200515024","https://openalex.org/W4206647757","https://openalex.org/W4251264660","https://openalex.org/W4288062174","https://openalex.org/W4312315996","https://openalex.org/W4312933868","https://openalex.org/W4313021454","https://openalex.org/W4377716587","https://openalex.org/W4381736219","https://openalex.org/W4385299582","https://openalex.org/W4386072096","https://openalex.org/W4386075999","https://openalex.org/W4390873054","https://openalex.org/W4394625844","https://openalex.org/W4399310923","https://openalex.org/W4402753751","https://openalex.org/W4402754201","https://openalex.org/W4402781669","https://openalex.org/W4402978275","https://openalex.org/W4403003241","https://openalex.org/W4404024902","https://openalex.org/W4404726022","https://openalex.org/W4405141746"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W2563206327","https://openalex.org/W2069885731"],"abstract_inverted_index":{"Image":[0],"outpainting,":[1],"a":[2,90,116],"challenging":[3],"generative":[4],"task,":[5],"has":[6],"advanced":[7],"significantly":[8],"with":[9],"the":[10,24,35,69,100,104,109,121,135,156,167],"introduction":[11],"of":[12,71,103,111,123],"text-to-image":[13],"diffusion":[14],"models":[15],"(DM).":[16],"Despite":[17],"these":[18],"advances,":[19],"DM-based":[20],"methods":[21],"frequently":[22],"encounter":[23],"phenomenon":[25],"in":[26,172],"which":[27,138],"one":[28],"modal":[29],"takes":[30],"precedence":[31],"over":[32],"another,":[33],"causing":[34],"image":[36,161,168],"to":[37,46,57,98,119],"be":[38],"over-guided.":[39],"Current":[40],"research":[41],"relies":[42],"on":[43,95,159],"manual":[44],"hyperparameters":[45],"achieve":[47,155],"bimodal":[48,60,72,81],"balance.":[49,173],"To":[50],"reduce":[51],"reliance,":[52],"Prompt":[53],"Libra":[54],"is":[55,139],"proposed":[56],"automatically":[58],"balance":[59],"prompts":[61,171],"during":[62,74],"inference":[63],"and":[64,107,169],"enhance":[65,108],"extrapolated":[66],"images.":[67,112],"Given":[68],"variation":[70],"cross-attention":[73],"DM":[75],"denoising,":[76],"we":[77,88,114],"create":[78],"an":[79],"adaptive":[80],"attention":[82,85],"module":[83],"via":[84],"maps.":[86],"Furthermore,":[87],"design":[89],"classifier-free":[91],"guidance":[92],"computation":[93],"based":[94],"masked":[96,105],"images":[97,153],"improve":[99],"semantic":[101,117],"control":[102],"part":[106],"quality":[110,124,162],"Finally,":[113],"propose":[115],"transformer":[118],"address":[120],"problem":[122],"degradation":[125],"caused":[126],"by":[127],"incomplete":[128],"prompts.":[129,145],"It":[130],"extracts":[131],"limited":[132],"semantics":[133],"from":[134],"source":[136],"images,":[137],"suitable":[140],"for":[141],"scenarios":[142],"lacking":[143],"text":[144,170],"Experimental":[146],"results":[147],"demonstrate":[148],"that":[149,154],"our":[150],"method":[151],"generates":[152],"state-of-the-art":[157],"effect":[158],"several":[160],"evaluation":[163],"metrics":[164],"while":[165],"maintaining":[166]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
