{"id":"https://openalex.org/W4414539443","doi":"https://doi.org/10.23919/mva65244.2025.11175076","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","display_name":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","publication_year":2025,"publication_date":"2025-07-26","ids":{"openalex":"https://openalex.org/W4414539443","doi":"https://doi.org/10.23919/mva65244.2025.11175076"},"language":"en","primary_location":{"id":"doi:10.23919/mva65244.2025.11175076","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva65244.2025.11175076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009707168","display_name":"Kaisheng Wu","orcid":"https://orcid.org/0000-0001-9741-7125"},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]},{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kuanting Wu","raw_affiliation_strings":["Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Tokyo","institution_ids":["https://openalex.org/I161296585","https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055154952","display_name":"Kei Ota","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kei Ota","raw_affiliation_strings":["Mitsubishi Electric"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045505869","display_name":"Asako Kanezaki","orcid":"https://orcid.org/0000-0003-3217-1405"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Asako Kanezaki","raw_affiliation_strings":["Science Tokyo & RIKEN AIP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science Tokyo & RIKEN AIP","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":"1","last_page":"6"},"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":0.8033999800682068,"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":0.8033999800682068,"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/T12100","display_name":"Advanced Mathematical Modeling in Engineering","score":0.7660999894142151,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.7468000054359436,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.6474999785423279},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.628600001335144},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6241000294685364},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.5972999930381775},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5026999711990356},{"id":"https://openalex.org/keywords/video-denoising","display_name":"Video denoising","score":0.4530999958515167},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.4262000024318695},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.42570000886917114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7081000208854675},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.6474999785423279},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.628600001335144},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6241000294685364},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5972999930381775},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48829999566078186},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.4530999958515167},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4203000068664551},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3571000099182129},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.35010001063346863},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2879999876022339},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/mva65244.2025.11175076","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva65244.2025.11175076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1904063580","https://openalex.org/W2064076387","https://openalex.org/W2133665775","https://openalex.org/W2760103357","https://openalex.org/W2962785568","https://openalex.org/W3034379322","https://openalex.org/W4386071957","https://openalex.org/W4386076323","https://openalex.org/W4386076483","https://openalex.org/W4390873054","https://openalex.org/W4390874580","https://openalex.org/W4400573519","https://openalex.org/W4400582084","https://openalex.org/W4402704510","https://openalex.org/W4402727415","https://openalex.org/W4402753907","https://openalex.org/W4402753964","https://openalex.org/W4402961675","https://openalex.org/W4403021266","https://openalex.org/W4409367532","https://openalex.org/W4412587524","https://openalex.org/W4413145386","https://openalex.org/W4413145932","https://openalex.org/W4413156212","https://openalex.org/W4413917052","https://openalex.org/W4414198939"],"related_works":[],"abstract_inverted_index":{"Video":[0],"Diffusion":[1],"Models":[2],"(VDMs)":[3],"can":[4],"generate":[5],"high-quality":[6],"videos,":[7],"but":[8],"often":[9],"struggle":[10],"with":[11,26],"producing":[12],"temporally":[13],"coherent":[14],"motion.":[15],"Optical":[16],"flow":[17,36,50,64,80],"supervision":[18,111],"is":[19],"a":[20,73],"promising":[21],"approach":[22],"to":[23],"address":[24],"this,":[25],"prior":[27],"works":[28],"commonly":[29],"employing":[30],"warping-based":[31],"strategies":[32],"that":[33,77,91],"avoid":[34],"explicit":[35],"matching.":[37],"In":[38],"this":[39],"work,":[40],"we":[41,71],"explore":[42],"an":[43],"alternative":[44],"formulation,":[45],"FlowLoss,":[46],"which":[47],"directly":[48],"compares":[49],"fields":[51],"extracted":[52],"from":[53],"generated":[54],"and":[55,96],"ground-truth":[56],"videos.":[57],"To":[58],"account":[59],"for":[60,108],"the":[61,79],"unreliability":[62],"of":[63],"estimation":[65],"under":[66],"high-noise":[67],"conditions":[68],"in":[69,99],"diffusion,":[70],"propose":[72],"noise-aware":[74],"weighting":[75],"scheme":[76],"modulates":[78],"loss":[81],"across":[82],"denoising":[83],"steps.":[84],"Experiments":[85],"on":[86],"robotic":[87],"video":[88],"datasets":[89],"suggest":[90],"FlowLoss":[92],"improves":[93],"motion":[94],"stability":[95],"accelerates":[97],"convergence":[98],"early":[100],"training":[101],"stages.":[102],"Our":[103],"findings":[104],"offer":[105],"practical":[106],"insights":[107],"incorporating":[109],"motion-based":[110],"into":[112],"noise-conditioned":[113],"generative":[114],"models.":[115]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}