{"id":"https://openalex.org/W7147024349","doi":"https://doi.org/10.48550/arxiv.2603.29736","title":"Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offs","display_name":"Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offs","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7147024349","doi":"https://doi.org/10.48550/arxiv.2603.29736"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.29736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29736","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.2603.29736","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132649086","display_name":"Yi Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hu, Yi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119720770","display_name":"Leying Yi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi, Leying","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132621406","display_name":"Emily Davis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davis, Emily","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132613442","display_name":"Finn Carter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carter, Finn","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5132649086"],"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":0.5551000237464905,"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":0.5551000237464905,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.030700000002980232,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.03060000017285347,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.5367000102996826},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.47540000081062317},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.46299999952316284},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4408999979496002},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4018000066280365},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3553999960422516},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.34200000762939453},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.3212999999523163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775999903678894},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4756999909877777},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.46299999952316284},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3375000059604645},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.2800000011920929},{"id":"https://openalex.org/C128107574","wikidata":"https://www.wikidata.org/wiki/Q182003","display_name":"Injective function","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.29736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29736","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.2603.29736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29736","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion-based":[0],"editing":[1,104,116],"has":[2],"rapidly":[3],"evolved":[4],"from":[5],"curated":[6],"inpainting":[7],"tools":[8],"into":[9],"general-purpose":[10],"editors":[11],"spanning":[12],"text-guided":[13],"instruction":[14,132],"following,":[15],"mask-localized":[16],"edits,":[17],"drag-based":[18],"geometric":[19],"manipulation,":[20],"exemplar":[21],"transfer,":[22],"and":[23,47,68,75,80,88,127,138,153,159,165,193,202],"training-free":[24],"composition":[25],"systems.":[26],"Despite":[27],"strong":[28],"empirical":[29,89],"progress,":[30],"the":[31,49,160,181],"field":[32],"lacks":[33],"a":[34,86,100,109,122],"unified":[35],"treatment":[36],"of":[37,66,73,91,103,162],"core":[38],"desiderata":[39],"that":[40],"govern":[41],"practical":[42],"usability:":[43],"controllability":[44],"(how":[45],"precisely":[46],"continuously":[48],"user":[50,57],"can":[51],"specify":[52],"an":[53,118],"edit),":[54],"faithfulness":[55],"to":[56,61,196],"intent":[58],"(semantic":[59],"alignment":[60],"instructions),":[62],"semantic":[63,136],"consistency":[64],"(preservation":[65],"identity":[67],"non-target":[69,200],"content),":[70],"locality":[71,167],"(containment":[72],"changes),":[74],"perceptual":[76],"quality":[77],"(artifact":[78],"suppression":[79],"detail":[81],"retention).":[82],"This":[83],"paper":[84],"provides":[85],"theoretical":[87],"analysis":[90],"general":[92],"diffusion-based":[93],"image":[94,111],"editing,":[95],"connecting":[96,190],"diverse":[97],"paradigms":[98],"through":[99],"common":[101],"view":[102],"as":[105,117],"guided":[106],"transport":[107],"on":[108,180],"learned":[110,182],"manifold.":[112],"We":[113,143],"first":[114],"formalize":[115],"operator":[119],"induced":[120],"by":[121],"conditional":[123],"reverse-time":[124],"generative":[125],"process":[126],"define":[128],"task-agnostic":[129],"metrics":[130],"capturing":[131],"adherence,":[133],"region":[134],"preservation,":[135],"consistency,":[137],"stability":[139],"under":[140,150,207],"repeated":[141],"edits.":[142],"then":[144],"develop":[145],"theory":[146],"describing":[147],"edit":[148],"dynamics":[149],"(i)":[151],"noise-injection":[152],"denoising":[154],"transport,":[155],"(ii)":[156],"inversion-and-edit":[157],"pipelines":[158],"propagation":[161],"inversion":[163,194],"errors,":[164],"(iii)":[166],"constraints":[168],"implemented":[169],"via":[170],"masked":[171],"guidance":[172,191],"or":[173,184],"hard":[174],"constraints.":[175],"Under":[176],"mild":[177],"Lipschitz":[178],"assumptions":[179],"score":[183],"flow":[185],"field,":[186],"we":[187,203,212],"derive":[188],"bounds":[189],"strength":[192],"error":[195],"measurable":[197],"deviations":[198],"in":[199],"regions,":[201],"characterize":[204],"accumulation":[205],"effects":[206],"iterative":[208],"multi-turn":[209],"editing.":[210],"Empirically,":[211],"benchmark":[213],"representative":[214],"paradigms.":[215]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}
