{"id":"https://openalex.org/W7131424940","doi":"https://doi.org/10.48550/arxiv.2602.20583","title":"PropFly: Learning to Propagate via On-the-Fly Supervision from Pre-trained Video Diffusion Models","display_name":"PropFly: Learning to Propagate via On-the-Fly Supervision from Pre-trained Video Diffusion Models","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7131424940","doi":"https://doi.org/10.48550/arxiv.2602.20583"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2602.20583","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.20583","pdf_url":"https://arxiv.org/pdf/2602.20583","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/2602.20583","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030910755","display_name":"Wonyong Seo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seo, Wonyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112519748","display_name":"Jae-Ho Moon","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moon, Jaeho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002247218","display_name":"Jaehyup Lee","orcid":"https://orcid.org/0000-0002-2137-2650","observed_orcids":["https://orcid.org/0000-0002-2137-2650"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Jaehyup","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126839771","display_name":"Soo Ye Kim","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Soo Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121164204","display_name":"Munchurl Kim","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Munchurl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":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/T12357","display_name":"Digital Media Forensic Detection","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/T11019","display_name":"Image Enhancement Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/video-diffusion-models","display_name":"video diffusion models","score":0.9539999961853027},{"id":"https://openalex.org/keywords/classifier-free-guidance","display_name":"classifier-free guidance","score":0.7269999980926514},{"id":"https://openalex.org/keywords/temporal-coherence","display_name":"temporal coherence","score":0.6079999804496765},{"id":"https://openalex.org/keywords/adapter-fine-tuning","display_name":"adapter fine-tuning","score":0.5090000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833899974822998},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6482999920845032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579000115394592},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5001000165939331},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4740000069141388},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4542999863624573},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.34860000014305115},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.3199000060558319},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25940001010894775},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.20583","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.20583","pdf_url":"https://arxiv.org/pdf/2602.20583","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.2602.20583","doi":"https://doi.org/10.48550/arxiv.2602.20583","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.20583","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.20583","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.20583","pdf_url":"https://arxiv.org/pdf/2602.20583","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Propagation-based":[0,54],"video":[1,36,55,63,74,185],"editing":[2,75,186,190],"enables":[3,130],"precise":[4],"user":[5],"control":[6],"by":[7],"propagating":[8],"a":[9,50],"single":[10],"edited":[11,119],"frame":[12],"into":[13],"following":[14],"frames":[15],"while":[16,117],"maintaining":[17],"the":[18,48,115,118,122,136,152,156,163,180],"original":[19],"context":[20],"such":[21,28],"as":[22,111],"motion":[23],"and":[24,34,41,102,169],"structures.":[25],"However,":[26],"training":[27,51],"models":[29,65],"requires":[30],"large-scale,":[31],"paired":[32,73],"(source":[33],"edited)":[35],"datasets,":[37],"which":[38,150],"are":[39],"costly":[40],"complex":[42],"to":[43,95,135,139,141,154,165],"acquire.":[44],"Hence,":[45],"we":[46],"propose":[47],"PropFly,":[49],"pipeline":[52,129],"for":[53,125],"editing,":[56],"relying":[57],"on":[58,183],"on-the-Fly":[59],"supervision":[60,161],"from":[61,85],"pre-trained":[62,137],"diffusion":[64],"(VDMs)":[66],"instead":[67],"of":[68,99,114],"requiring":[69],"off-the-shelf":[70],"or":[71],"precomputed":[72],"datasets.":[76],"Specifically,":[77],"our":[78,176],"PropFly":[79,177],"leverages":[80],"one-step":[81],"clean":[82],"latent":[83,109,120],"estimations":[84],"intermediate":[86],"noised":[87],"latents":[88,105],"with":[89],"varying":[90],"Classifier-Free":[91],"Guidance":[92],"(CFG)":[93],"scales":[94],"synthesize":[96],"diverse":[97],"pairs":[98],"'source'":[100],"(low-CFG)":[101],"'edited'":[103],"(high-CFG)":[104],"on-the-fly.":[106],"The":[107],"source":[108],"serves":[110],"structural":[112],"information":[113],"video,":[116],"provides":[121],"target":[123,157],"transformation":[124],"learning":[126],"propagation.":[127],"Our":[128,159],"an":[131],"additional":[132],"adapter":[133],"attached":[134],"VDM":[138],"learn":[140,166],"propagate":[142],"edits":[143],"via":[144],"Guidance-Modulated":[145],"Flow":[146],"Matching":[147],"(GMFM)":[148],"loss,":[149],"guides":[151],"model":[153,164],"replicate":[155],"transformation.":[158],"on-the-fly":[160],"ensures":[162],"temporally":[167],"consistent":[168],"dynamic":[170],"transformations.":[171],"Extensive":[172],"experiments":[173],"demonstrate":[174],"that":[175],"significantly":[178],"outperforms":[179],"state-of-the-art":[181],"methods":[182],"various":[184],"tasks,":[187],"producing":[188],"high-quality":[189],"results.":[191]},"counts_by_year":[],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2026-02-26T00:00:00"}