{"id":"https://openalex.org/W7141004745","doi":"https://doi.org/10.48550/arxiv.2603.25527","title":"Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training","display_name":"Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141004745","doi":"https://doi.org/10.48550/arxiv.2603.25527"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.25527","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25527","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.25527","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130795567","display_name":"Xiangyang Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Xiangyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130764164","display_name":"Qingyu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Qingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130781849","display_name":"Yuming Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yuming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111830185","display_name":"Guanbo Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Guanbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101873047","display_name":"Yongjie Zhu","orcid":"https://orcid.org/0000-0002-3828-6839"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yongjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130736204","display_name":"Wenyu Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Wenyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130772838","display_name":"Meng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130783984","display_name":"Pengfei Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Pengfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130807463","display_name":"Shao-Lun Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shao-Lun","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":0.8973000049591064,"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":0.8973000049591064,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.02370000071823597,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.014000000432133675,"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/quality","display_name":"Quality (philosophy)","score":0.5961999893188477},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5040000081062317},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4713999927043915},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.46939998865127563},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.4684999883174896},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4580000042915344},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3824999928474426},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.34130001068115234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7718999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6362000107765198},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6207000017166138},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5040000081062317},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4713999927043915},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3637999892234802},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C114227958","wikidata":"https://www.wikidata.org/wiki/Q7631422","display_name":"Subjective video quality","level":4,"score":0.2973000109195709},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2619999945163727},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.25527","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25527","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":"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":"doi:10.48550/arxiv.2603.25527","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25527","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":"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"},"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":{"Recent":[0],"advances":[1],"in":[2,39,69,120,201],"video":[3,40,84,202],"generation":[4],"models":[5,12,86],"have":[6],"achieved":[7],"impressive":[8],"results.":[9],"However,":[10],"these":[11],"heavily":[13],"rely":[14],"on":[15,91,110,182,213],"the":[16,43,79,114,131,138,147,196],"use":[17],"of":[18,83,117,145,198],"high-quality":[19,214],"data":[20,41,66,98,105,132,162,185,200,221],"that":[21,49,67,96,177],"combines":[22],"both":[23,70],"high":[24,28,159],"visual":[25,50,160],"quality":[26,51,161],"and":[27,52,87],"motion":[29,53],"quality.":[30],"In":[31],"this":[32,74],"paper,":[33],"we":[34,76,112,175],"identify":[35],"a":[36,57],"key":[37],"challenge":[38],"curation:":[42],"Motion-Vision":[44],"Quality":[45,126],"Dilemma.":[46],"We":[47,94,123],"discovered":[48],"intensity":[54],"inherently":[55],"exhibit":[56],"negative":[58],"correlation,":[59],"making":[60],"it":[61],"hard":[62],"to":[63,103,135,166,186],"obtain":[64],"golden":[65,104],"excels":[68],"aspects.":[71],"To":[72],"address":[73],"challenge,":[75],"first":[77],"examine":[78],"hierarchical":[80],"learning":[81,140],"dynamics":[82],"diffusion":[85],"conduct":[88],"gradient-based":[89],"analysis":[90],"quality-degraded":[92],"samples.":[93],"discover":[95],"quality-imbalanced":[97],"can":[99],"produce":[100],"gradients":[101],"similar":[102],"at":[106],"appropriate":[107],"timesteps.":[108,171],"Based":[109],"this,":[111],"introduce":[113],"novel":[115],"concept":[116],"Timestep":[118],"selection":[119],"Training":[121],"Process.":[122],"propose":[124],"Timestep-aware":[125],"Decoupling":[127],"(TQD),":[128],"which":[129],"modifies":[130],"sampling":[133,148],"distribution":[134,149],"better":[136,193],"match":[137],"model's":[139],"process.":[141],"For":[142],"certain":[143],"types":[144],"data,":[146,157,194,215],"is":[150,163],"skewed":[151],"toward":[152],"higher":[153],"timesteps":[154],"for":[155],"motion-rich":[156],"while":[158],"more":[164],"likely":[165],"be":[167],"sampled":[168],"during":[169],"lower":[170],"Through":[172],"extensive":[173],"experiments,":[174],"demonstrate":[176],"TQD":[178],"enables":[179],"training":[180,191],"exclusively":[181],"separated":[183],"imbalanced":[184],"achieve":[187],"performance":[188,210],"surpassing":[189],"conventional":[190],"with":[192],"challenging":[195],"necessity":[197],"perfect":[199],"generation.":[203],"Moreover,":[204],"our":[205],"method":[206],"also":[207],"boosts":[208],"model":[209],"when":[211],"trained":[212],"showcasing":[216],"its":[217],"effectiveness":[218],"across":[219],"different":[220],"scenarios.":[222]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-28T00:00:00"}