{"id":"https://openalex.org/W7137891857","doi":"https://doi.org/10.48550/arxiv.2603.13388","title":"VeloEdit: Training-Free Consistent and Continuous Instruction-Based Image Editing via Velocity Field Decomposition","display_name":"VeloEdit: Training-Free Consistent and Continuous Instruction-Based Image Editing via Velocity Field Decomposition","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7137891857","doi":"https://doi.org/10.48550/arxiv.2603.13388"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.13388","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.13388","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126081392","display_name":"Zongqing Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zongqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082206789","display_name":"ZhiHui Liu","orcid":"https://orcid.org/0009-0001-3664-3185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhihui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129664832","display_name":"Yujie Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Yujie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128010669","display_name":"Shansiyuan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Shansiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127925478","display_name":"Hongshen Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Hongshen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125134939","display_name":"Songzhi Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Songzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.7364000082015991,"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":0.7364000082015991,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.042500000447034836,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.022199999541044235,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6377000212669373},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6273999810218811},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.49219998717308044},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46459999680519104},{"id":"https://openalex.org/keywords/vector-field","display_name":"Vector field","score":0.4611000120639801},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4577000141143799},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41589999198913574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.656499981880188},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6377000212669373},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6273999810218811},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49549999833106995},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C91188154","wikidata":"https://www.wikidata.org/wiki/Q186247","display_name":"Vector field","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4449999928474426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3921000063419342},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.30079999566078186},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C93038891","wikidata":"https://www.wikidata.org/wiki/Q1061524","display_name":"Intensity (physics)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C2780967703","wikidata":"https://www.wikidata.org/wiki/Q2571389","display_name":"Collaborative editing","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.13388","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.13388","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4048393666744232}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Instruction-based":[0],"image":[1],"editing":[2,68,102,155],"aims":[3],"to":[4,9,21,28],"modify":[5],"source":[6,81],"content":[7,82],"according":[8],"textual":[10],"instructions.":[11],"However,":[12],"existing":[13],"methods":[14],"built":[15],"upon":[16],"flow":[17],"matching":[18],"often":[19],"struggle":[20],"maintain":[22],"consistency":[23,95,153],"in":[24,35,96,115],"non-edited":[25],"regions":[26,69,98,117],"due":[27],"denoising-induced":[29],"reconstruction":[30],"errors":[31],"that":[32,57,124,149],"cause":[33],"drift":[34],"preserved":[36],"content.":[37],"Moreover,":[38],"they":[39],"typically":[40],"lack":[41],"fine-grained":[42],"control":[43],"over":[44],"edit":[45,113],"strength.":[46],"To":[47],"address":[48],"these":[49],"limitations,":[50],"we":[51,93],"propose":[52],"VeloEdit,":[53],"a":[54],"training-free":[55],"method":[56],"enables":[58],"highly":[59],"consistent":[60],"and":[61,83,146,154],"continuously":[62],"controllable":[63],"editing.":[64],"VeloEdit":[65,134,150],"dynamically":[66],"identifies":[67],"by":[70,99],"quantifying":[71],"the":[72,75,86,101,105,138],"discrepancy":[73],"between":[74],"velocity":[76,103,119,139],"fields":[77],"responsible":[78],"for":[79],"preserving":[80],"those":[84],"driving":[85],"desired":[87],"edits.":[88],"Based":[89],"on":[90,126,137,143],"this":[91],"partition,":[92],"enforce":[94],"preservation":[97],"substituting":[100],"with":[104,157],"source-restoring":[106],"velocity,":[107],"while":[108],"enabling":[109],"continuous":[110],"modulation":[111],"of":[112],"intensity":[114],"target":[116],"via":[118],"interpolation.":[120],"Unlike":[121],"prior":[122],"works":[123],"rely":[125],"complex":[127],"attention":[128],"manipulation":[129],"or":[130],"auxiliary":[131],"trainable":[132],"modules,":[133],"operates":[135],"directly":[136],"fields.":[140],"Extensive":[141],"experiments":[142],"Flux.1":[144],"Kontext":[145],"Qwen-Image-Edit":[147],"demonstrate":[148],"improves":[151],"visual":[152],"continuity":[156],"negligible":[158],"additional":[159],"computational":[160],"cost.":[161],"Code":[162],"is":[163],"available":[164],"at":[165],"https://github.com/xmulzq/VeloEdit.":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}