{"id":"https://openalex.org/W4404985109","doi":"https://doi.org/10.1145/3680528.3687668","title":"InstantDrag: Improving Interactivity in Drag-based Image Editing","display_name":"InstantDrag: Improving Interactivity in Drag-based Image Editing","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4404985109","doi":"https://doi.org/10.1145/3680528.3687668"},"language":"en","primary_location":{"id":"doi:10.1145/3680528.3687668","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3680528.3687668","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3680528.3687668","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2024 Conference Papers","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/10.1145/3680528.3687668","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048498202","display_name":"Joonghyuk Shin","orcid":"https://orcid.org/0000-0003-3780-3897"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonghyuk Shin","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-3780-3897","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103497771","display_name":"D. Y. Choi","orcid":"https://orcid.org/0009-0003-1438-4949"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daehyeon Choi","raw_affiliation_strings":["POSTECH, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0009-0003-1438-4949","affiliations":[{"raw_affiliation_string":"POSTECH, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100611457","display_name":"Jaesik Park","orcid":"https://orcid.org/0000-0001-5541-409X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaesik Park","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-5541-409X","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1035,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91337335,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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":0.9987000226974487,"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":0.9987000226974487,"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":0.998199999332428,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9922999739646912,"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/interactivity","display_name":"Interactivity","score":0.8746053576469421},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6940133571624756},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5871129631996155},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5166288018226624},{"id":"https://openalex.org/keywords/drag","display_name":"Drag","score":0.4904136657714844},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.44251909852027893},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.43769627809524536},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3579595685005188},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3270156681537628},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14146313071250916},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.07331481575965881}],"concepts":[{"id":"https://openalex.org/C144430266","wikidata":"https://www.wikidata.org/wiki/Q839721","display_name":"Interactivity","level":2,"score":0.8746053576469421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940133571624756},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5871129631996155},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5166288018226624},{"id":"https://openalex.org/C72921944","wikidata":"https://www.wikidata.org/wiki/Q206621","display_name":"Drag","level":2,"score":0.4904136657714844},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.44251909852027893},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.43769627809524536},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3579595685005188},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3270156681537628},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14146313071250916},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.07331481575965881}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3680528.3687668","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3680528.3687668","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3680528.3687668","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2024 Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/217137","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/217137","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Proceedings Paper"}],"best_oa_location":{"id":"doi:10.1145/3680528.3687668","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3680528.3687668","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3680528.3687668","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2024 Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404985109.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W764651262","https://openalex.org/W1513100184","https://openalex.org/W2962785568","https://openalex.org/W2962793481","https://openalex.org/W2963037989","https://openalex.org/W2963073614","https://openalex.org/W3035574324","https://openalex.org/W3173102319","https://openalex.org/W3180770160","https://openalex.org/W4312790276","https://openalex.org/W4312933868","https://openalex.org/W4385535562","https://openalex.org/W4386071464","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4402660159","https://openalex.org/W4402702967","https://openalex.org/W4402716373","https://openalex.org/W6600669965","https://openalex.org/W6600864179"],"related_works":["https://openalex.org/W1578944177","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/W3015353979"],"abstract_inverted_index":{"Drag-based":[0],"image":[1,41,90,123,138,174],"editing":[2,26,74,124],"has":[3],"recently":[4],"gained":[5],"popularity":[6],"for":[7,62,121,181],"its":[8],"interactivity":[9,71,84],"and":[10,65,85,91,110,136,160],"precision.":[11],"However,":[12],"despite":[13],"the":[14,32,70,73,131,166],"ability":[15],"of":[16,34,72,99,168],"text-to-image":[17],"models":[18],"to":[19,31,144],"generate":[20],"samples":[21],"within":[22],"a":[23,92,104,178],"second,":[24],"drag":[25,93],"still":[27],"lags":[28],"behind":[29],"due":[30],"challenge":[33],"accurately":[35],"reflecting":[36],"user":[37],"interaction":[38],"while":[39],"maintaining":[40],"content.":[42],"Some":[43],"existing":[44],"approaches":[45],"rely":[46],"on":[47,156],"computationally":[48],"intensive":[49],"per-image":[50],"optimization":[51],"or":[52,151],"intricate":[53],"guidance-based":[54],"methods,":[55],"requiring":[56,87],"additional":[57],"inputs":[58],"such":[59],"as":[60,95],"masks":[61,150],"movable":[63],"regions":[64],"text":[66,152],"prompts,":[67],"thereby":[68],"compromising":[69],"process.":[75],"We":[76,140],"introduce":[77],"InstantDrag,":[78],"an":[79,89,111],"optimization-free":[80],"pipeline":[81],"that":[82],"enhances":[83],"speed,":[86],"only":[88],"instruction":[94],"input.":[96],"InstantDrag":[97,117],"consists":[98],"two":[100],"carefully":[101],"designed":[102],"networks:":[103],"drag-conditioned":[105],"optical":[106,112],"flow":[107],"generator":[108],"(FlowGen)":[109],"flow-conditioned":[113],"diffusion":[114],"model":[115],"(FlowDiffusion).":[116],"learns":[118],"motion":[119,134],"dynamics":[120],"drag-based":[122,173],"in":[125,171],"real-world":[126],"video":[127,158],"datasets":[128,159],"by":[129],"decomposing":[130],"task":[132],"into":[133],"generation":[135],"motion-conditioned":[137],"generation.":[139],"demonstrate":[141],"InstantDrags":[142],"capability":[143],"perform":[145],"fast,":[146],"photo-realistic":[147],"edits":[148],"without":[149],"prompts":[153],"through":[154],"experiments":[155],"facial":[157],"general":[161],"scenes.":[162],"These":[163],"results":[164],"highlight":[165],"efficiency":[167],"our":[169],"approach":[170],"handling":[172],"editing,":[175],"making":[176],"it":[177],"promising":[179],"solution":[180],"interactive,":[182],"real-time":[183],"applications.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}