{"id":"https://openalex.org/W4392902661","doi":"https://doi.org/10.1109/icassp48485.2024.10446377","title":"Grounded-Instruct-Pix2Pix: Improving Instruction Based Image Editing with Automatic Target Grounding","display_name":"Grounded-Instruct-Pix2Pix: Improving Instruction Based Image Editing with Automatic Target Grounding","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902661","doi":"https://doi.org/10.1109/icassp48485.2024.10446377"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5094178883","display_name":"Artur Shagidanov","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Artur Shagidanov","raw_affiliation_strings":["Picsart AI Research (PAIR)"],"affiliations":[{"raw_affiliation_string":"Picsart AI Research (PAIR)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031157061","display_name":"Hayk Poghosyan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hayk Poghosyan","raw_affiliation_strings":["Picsart AI Research (PAIR)"],"affiliations":[{"raw_affiliation_string":"Picsart AI Research (PAIR)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103086800","display_name":"Xinyu Gong","orcid":"https://orcid.org/0000-0002-6993-136X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyu Gong","raw_affiliation_strings":["UT Austin","Picsart AI Research (PAIR)"],"affiliations":[{"raw_affiliation_string":"UT Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Picsart AI Research (PAIR)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048522863","display_name":"Zhangyang Wang","orcid":"https://orcid.org/0000-0002-2050-5693"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhangyang Wang","raw_affiliation_strings":["Picsart AI Research (PAIR)","UT Austin"],"affiliations":[{"raw_affiliation_string":"Picsart AI Research (PAIR)","institution_ids":[]},{"raw_affiliation_string":"UT Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036843155","display_name":"Shant Navasardyan","orcid":"https://orcid.org/0000-0002-1999-9999"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shant Navasardyan","raw_affiliation_strings":["Picsart AI Research (PAIR)"],"affiliations":[{"raw_affiliation_string":"Picsart AI Research (PAIR)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002072267","display_name":"Humphrey Shi","orcid":"https://orcid.org/0000-0002-2922-5663"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Humphrey Shi","raw_affiliation_strings":["Picsart AI Research (PAIR)","Georgia Tech"],"affiliations":[{"raw_affiliation_string":"Picsart AI Research (PAIR)","institution_ids":[]},{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5094178883"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3562,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89244541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6585","last_page":"6589"},"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":0.9984999895095825,"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":0.9984999895095825,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9641000032424927,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9524999856948853,"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":0.7358068227767944},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5934217572212219},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5326882004737854},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5190985202789307},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.4997711181640625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36281466484069824},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3491339087486267},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.322060227394104},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10188740491867065},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08262565732002258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7358068227767944},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5934217572212219},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5326882004737854},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5190985202789307},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4997711181640625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36281466484069824},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3491339087486267},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.322060227394104},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10188740491867065},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08262565732002258},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2962785568","https://openalex.org/W3036167779","https://openalex.org/W3121370741","https://openalex.org/W3153469116","https://openalex.org/W3155072588","https://openalex.org/W3162926177","https://openalex.org/W4224035735","https://openalex.org/W4281485151","https://openalex.org/W4289785045","https://openalex.org/W4312933868","https://openalex.org/W4318203092","https://openalex.org/W4321854185","https://openalex.org/W4361865257","https://openalex.org/W4363671609","https://openalex.org/W4378771069","https://openalex.org/W4385271281","https://openalex.org/W4385527149","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4390872477","https://openalex.org/W4390873195","https://openalex.org/W4390873429","https://openalex.org/W4390874575","https://openalex.org/W4404612908","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6795288823","https://openalex.org/W6809885388","https://openalex.org/W6838639034","https://openalex.org/W6841366371","https://openalex.org/W6848774630","https://openalex.org/W6850108851","https://openalex.org/W6850787431","https://openalex.org/W6851457070","https://openalex.org/W6852305316","https://openalex.org/W6852520045"],"related_works":["https://openalex.org/W4319453795","https://openalex.org/W4205104112","https://openalex.org/W1974870326","https://openalex.org/W2770776392","https://openalex.org/W3176454756","https://openalex.org/W2772330423","https://openalex.org/W3163523050","https://openalex.org/W3006381446","https://openalex.org/W4386301887","https://openalex.org/W3015353979"],"abstract_inverted_index":{"Text-guided":[0],"Image":[1],"Editing":[2],"has":[3],"recently":[4],"attracted":[5],"significant":[6],"attention":[7],"due":[8],"to":[9,22,39,44,106],"advances":[10],"in":[11,51,74],"the":[12,41,46,52,96,103,107],"denoising":[13],"diffusion":[14],"models":[15],"field.":[16],"Current":[17],"methods":[18],"make":[19],"it":[20],"possible":[21],"execute":[23],"complex":[24,81],"image":[25,72],"editing":[26,73,104],"operations":[27],"with":[28],"simple":[29],"text":[30,53],"prompts.":[31],"But":[32],"despite":[33],"impressive":[34],"results,":[35],"they":[36],"often":[37],"fail":[38],"restrict":[40],"edit":[42],"area":[43,108],"only":[45],"object":[47],"of":[48,69,89,109],"interest,":[49],"specified":[50],"prompt.":[54],"To":[55],"this":[56],"end,":[57],"we":[58,63],"propose":[59],"a":[60,86],"novel":[61],"framework":[62],"name":[64],"Grounded-Instruct-Pix2Pix,":[65],"which":[66],"is":[67],"capable":[68],"localized":[70],"instruction-guided":[71],"various":[75],"scenarios":[76],"including":[77],"multi-object":[78],"cases":[79],"and":[80],"backgrounds.":[82],"Our":[83],"experiments":[84],"on":[85],"diverse":[87],"set":[88],"images":[90],"clearly":[91],"showcase":[92],"its":[93],"advantage":[94],"over":[95],"recent":[97],"state-of-the-art":[98],"approaches,":[99],"especially":[100],"at":[101,117],"restricting":[102],"effect":[105],"interest":[110],"only.":[111],"Grounded-Instruct-Pix2Pix":[112],"implementation":[113],"will":[114],"be":[115],"available":[116],"https://github.com/arthur-71/Grounded-Instruct-Pix2Pix.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}