{"id":"https://openalex.org/W4385535562","doi":"https://doi.org/10.1145/3588432.3591500","title":"Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold","display_name":"Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold","publication_year":2023,"publication_date":"2023-07-19","ids":{"openalex":"https://openalex.org/W4385535562","doi":"https://doi.org/10.1145/3588432.3591500"},"language":"en","primary_location":{"id":"doi:10.1145/3588432.3591500","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588432.3591500","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591500","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591500","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052549072","display_name":"Xingang Pan","orcid":"https://orcid.org/0000-0002-5825-9467"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xingang Pan","raw_affiliation_strings":["Max Planck Institute for Informatics, Germany and Saarbr\u00fccken Research Center for Visual Computing, Interaction and AI, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5825-9467","affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Germany and Saarbr\u00fccken Research Center for Visual Computing, Interaction and AI, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075797855","display_name":"Ayush Tewari","orcid":"https://orcid.org/0000-0002-3805-4421"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayush Tewari","raw_affiliation_strings":["Massachusetts Institute of Technology, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-3805-4421","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, United States of America","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113193684","display_name":"Thomas Leimk\u00fchler","orcid":"https://orcid.org/0009-0006-7784-7957"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Leimk\u00fchler","raw_affiliation_strings":["Max Planck Institute for Informatics, Germany"],"raw_orcid":"https://orcid.org/0009-0006-7784-7957","affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087345525","display_name":"Lingjie Liu","orcid":"https://orcid.org/0000-0003-4301-1474"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Lingjie Liu","raw_affiliation_strings":["Max Planck Institute for Informatics, Germany and University of Pennsylvania, USA"],"raw_orcid":"https://orcid.org/0000-0003-4301-1474","affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Germany and University of Pennsylvania, USA","institution_ids":["https://openalex.org/I4210109712","https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067754015","display_name":"Abhimitra Meka","orcid":"https://orcid.org/0000-0001-7906-4004"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhimitra Meka","raw_affiliation_strings":["Google AR/VR, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-7906-4004","affiliations":[{"raw_affiliation_string":"Google AR/VR, United States of America","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020664641","display_name":"Christian Theobalt","orcid":"https://orcid.org/0000-0001-6104-6625"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Theobalt","raw_affiliation_strings":["Max Planck Institute for Informatics, Germany and Saarbr\u00fccken Research Center for Visual Computing, Interaction and AI, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6104-6625","affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Germany and Saarbr\u00fccken Research Center for Visual Computing, Interaction and AI, Germany","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":198,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9969000220298767,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9959999918937683,"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":0.7832812070846558},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6393051147460938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6386019587516785},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.4905330538749695},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4218599796295166},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.417780339717865},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.41007620096206665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832812070846558},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6393051147460938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6386019587516785},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.4905330538749695},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4218599796295166},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.417780339717865},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.41007620096206665},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3588432.3591500","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588432.3591500","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591500","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3588432.3591500","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588432.3591500","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591500","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[{"id":"https://openalex.org/G4362534776","display_name":null,"funder_award_id":"ERC Consolidator Grant 4DReply (770784)","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385535562.pdf","grobid_xml":"https://content.openalex.org/works/W4385535562.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1530781137","https://openalex.org/W2115252128","https://openalex.org/W2131747574","https://openalex.org/W2560474170","https://openalex.org/W2765811365","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2962974533","https://openalex.org/W2963073614","https://openalex.org/W2985068832","https://openalex.org/W3014859719","https://openalex.org/W3034371424","https://openalex.org/W3034431451","https://openalex.org/W3034600949","https://openalex.org/W3035574324","https://openalex.org/W3035653890","https://openalex.org/W3047371217","https://openalex.org/W3167788848","https://openalex.org/W3173102319","https://openalex.org/W3173531806","https://openalex.org/W3188353775","https://openalex.org/W3214564114","https://openalex.org/W3214748320","https://openalex.org/W4205249820","https://openalex.org/W4285981707","https://openalex.org/W4288065899","https://openalex.org/W4293575078","https://openalex.org/W4312326540","https://openalex.org/W4312453532","https://openalex.org/W4312933868","https://openalex.org/W4328029562"],"related_works":["https://openalex.org/W2036697162","https://openalex.org/W2332386680","https://openalex.org/W2248621902","https://openalex.org/W2003779889","https://openalex.org/W2561315646","https://openalex.org/W4205698120","https://openalex.org/W4239246781","https://openalex.org/W2542825942","https://openalex.org/W3201620972","https://openalex.org/W1496421768"],"abstract_inverted_index":{"Synthesizing":[0],"visual":[1],"content":[2,197],"that":[3,65,104,122,201],"meets":[4],"users\u2019":[5],"needs":[6],"often":[7,44],"requires":[8],"flexible":[9],"and":[10,18,48,115,157,198,209,226],"precise":[11,145],"controllability":[12,27],"of":[13,20,28,62,71,95,133,159,180,215,223,234],"the":[14,21,72,106,112,124,131,134,153,175,204,213,221,232],"pose,":[15,154],"shape,":[16,155],"expression,":[17,156],"layout":[19,158],"generated":[22],"objects.":[23],"Existing":[24],"approaches":[25,219],"gain":[26],"generative":[29,177],"adversarial":[30],"networks":[31],"(GANs)":[32],"via":[33],"manually":[34],"annotated":[35],"training":[36],"data":[37],"or":[38],"a":[39,55,80,100,117,181],"prior":[40,218],"3D":[41],"model,":[42],"which":[43,93],"lack":[45],"flexibility,":[46],"precision,":[47],"generality.":[49],"In":[50],"this":[51],"work,":[52],"we":[53,90],"study":[54],"powerful":[56],"yet":[57],"much":[58],"less":[59],"explored":[60],"way":[61],"controlling":[63],"GANs,":[64],"is,":[66],"to":[67,74,109,128,185],"\"drag\"":[68],"any":[69],"points":[70,78],"image":[73,143,178,224],"precisely":[75],"reach":[76],"target":[77,113],"in":[79,85,220],"user-interactive":[81],"manner,":[82],"as":[83,163,194],"shown":[84],"Fig.1.":[86],"To":[87],"achieve":[88],"this,":[89],"propose":[91],"DragGAN,":[92,138],"consists":[94],"two":[96],"main":[97],"components:":[98],"1)":[99],"feature-based":[101],"motion":[102],"supervision":[103],"drives":[105],"handle":[107,135],"point":[108,119,227],"move":[110],"towards":[111],"position,":[114],"2)":[116],"new":[118],"tracking":[120],"approach":[121],"leverages":[123],"discriminative":[125],"generator":[126],"features":[127],"keep":[129],"localizing":[130],"position":[132],"points.":[136],"Through":[137],"anyone":[139],"can":[140],"deform":[141],"an":[142],"with":[144],"control":[146],"over":[147,217],"where":[148],"pixels":[149],"go,":[150],"thus":[151],"manipulating":[152],"diverse":[160],"categories":[161],"such":[162,193],"animals,":[164],"cars,":[165],"humans,":[166],"landscapes,":[167],"etc.":[168],"As":[169],"these":[170],"manipulations":[171],"are":[172],"performed":[173],"on":[174],"learned":[176],"manifold":[179],"GAN,":[182],"they":[183],"tend":[184],"produce":[186],"realistic":[187],"outputs":[188],"even":[189],"for":[190],"challenging":[191],"scenarios":[192],"hallucinating":[195],"occluded":[196],"deforming":[199],"shapes":[200],"consistently":[202],"follow":[203],"object\u2019s":[205],"rigidity.":[206],"Both":[207],"qualitative":[208],"quantitative":[210],"comparisons":[211],"demonstrate":[212],"advantage":[214],"DragGAN":[216],"tasks":[222],"manipulation":[225,233],"tracking.":[228],"We":[229],"also":[230],"showcase":[231],"real":[235],"images":[236],"through":[237],"GAN":[238],"inversion.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":66},{"year":2024,"cited_by_count":100},{"year":2023,"cited_by_count":18}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}