{"id":"https://openalex.org/W7203702008","doi":"https://doi.org/10.48550/arxiv.2608.14740","title":"From Dense Prediction to Visual Editing: Structured Supervision for Unified Image and Video Creation","display_name":"From Dense Prediction to Visual Editing: Structured Supervision for Unified Image and Video Creation","publication_year":2026,"publication_date":"2026-08-13","ids":{"openalex":"https://openalex.org/W7203702008","doi":"https://doi.org/10.48550/arxiv.2608.14740"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.14740","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14740","pdf_url":"https://arxiv.org/pdf/2608.14740","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.14740","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063565443","display_name":"Zhefan Rao","orcid":"https://orcid.org/0000-0001-9579-8665","observed_orcids":["https://orcid.org/0000-0001-9579-8665"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rao, Zhefan","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133504699","display_name":"Bin Zou","orcid":"https://orcid.org/0000-0002-8649-1538","observed_orcids":["https://orcid.org/0000-0002-8649-1538","https://orcid.org/0000-0001-6135-3174"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Bin","raw_affiliation_strings":["Celia Research HK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Celia Research HK","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"He, Xuanhua","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"He, Xuanhua","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133543823","display_name":"Chong Hou Choi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choi, Chong Hou","raw_affiliation_strings":["Celia Research HK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Celia Research HK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133488427","display_name":"Yanheng Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Li, Yanheng","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147413688","display_name":"Yanheng Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Rui","raw_affiliation_strings":["Celia Research HK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Celia Research HK","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Che, Haoxuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Che, Haoxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100719529","display_name":"Qifeng Chen","orcid":"https://orcid.org/0000-0003-2199-3948","observed_orcids":["https://orcid.org/0000-0003-2199-3948","https://orcid.org/0000-0003-3439-0521"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen, Qifeng","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":1.0,"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":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-editing","display_name":"visual editing","score":0.8669999837875366},{"id":"https://openalex.org/keywords/depth-estimation","display_name":"depth estimation","score":0.9010000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950000166893005},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6431999802589417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5727999806404114},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5002999901771545},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4481000006198883},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3546000123023987},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.28949999809265137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.14740","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14740","pdf_url":"https://arxiv.org/pdf/2608.14740","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.14740","doi":"https://doi.org/10.48550/arxiv.2608.14740","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.14740","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.14740","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14740","pdf_url":"https://arxiv.org/pdf/2608.14740","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203702008.pdf","grobid_xml":"https://content.openalex.org/works/W7203702008.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7118934409","https://openalex.org/W4390874580","https://openalex.org/W7106783759","https://openalex.org/W6922599631","https://openalex.org/W4414565121","https://openalex.org/W7212271707","https://openalex.org/W4413147842","https://openalex.org/W7223013762","https://openalex.org/W7128618218","https://openalex.org/W7164030651"],"abstract_inverted_index":{"Unified":[0],"image":[1],"and":[2,16,25,45,94,109,138,165],"video":[3],"creation":[4,63],"requires":[5],"a":[6,90,95,148,173],"model":[7],"to":[8,105,136,143,159],"follow":[9],"diverse":[10],"instructions":[11],"while":[12,75],"preserving":[13],"identity,":[14],"geometry,":[15],"temporal":[17],"structure":[18,34],"from":[19,70,134,141],"visual":[20,58,73],"context.":[21],"However,":[22],"semantic-only":[23],"conditioning":[24],"creation-only":[26],"training":[27,97],"do":[28,168],"not":[29,169],"explicitly":[30],"supervise":[31],"the":[32,61,101,116,121],"local":[33],"needed":[35],"for":[36],"precise,":[37],"temporally":[38,106],"consistent":[39],"editing.":[40],"We":[41],"therefore":[42],"formulate":[43],"depth":[44],"surface-normal":[46],"prediction":[47],"as":[48,56,172],"image-form":[49],"denoising":[50],"targets,":[51],"using":[52],"these":[53],"dense":[54,129,153,175],"tasks":[55],"structured":[57],"supervision":[59,130,154],"within":[60],"same":[62],"interface.":[64],"Our":[65],"framework":[66],"decouples":[67],"semantic":[68],"interpretation":[69],"spatially":[71],"aligned":[72],"injection":[74],"sharing":[76],"one":[77],"multimodal":[78],"diffusion":[79],"transformer":[80],"(MMDiT)":[81],"backbone":[82],"across":[83],"all":[84],"tasks.":[85],"Mutual":[86],"Context":[87],"Attention":[88],"(MCA),":[89],"paired-video":[91],"data-construction":[92],"procedure,":[93],"progressive":[96],"curriculum":[98],"then":[99],"connect":[100],"learned":[102],"structural":[103,157],"cues":[104],"localized":[107],"editing":[108,163],"reference-conditioned":[110],"creation.":[111],"A":[112],"single":[113],"checkpoint":[114],"obtains":[115],"highest":[117],"overall":[118],"score":[119],"in":[120],"reported":[122],"comparison":[123],"of":[124],"unified":[125],"systems":[126],"(4.15);":[127],"adding":[128],"improves":[131],"OpenVE":[132],"Overall":[133],"3.98":[135],"4.06":[137],"Local":[139],"Add":[140],"3.92":[142],"4.18.":[144],"These":[145],"results":[146],"support":[147],"deliberately":[149],"bounded":[150],"conclusion:":[151],"perception-oriented":[152],"transfers":[155],"useful":[156],"knowledge":[158],"downstream":[160],"creation,":[161],"especially":[162],"locality":[164],"preservation;":[166],"we":[167],"claim":[170],"superiority":[171],"standalone":[174],"predictor.":[176]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-19T00:00:00"}
