{"id":"https://openalex.org/W7201870964","doi":"https://doi.org/10.48550/arxiv.2608.05565","title":"EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal","display_name":"EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal","publication_year":2026,"publication_date":"2026-08-06","ids":{"openalex":"https://openalex.org/W7201870964","doi":"https://doi.org/10.48550/arxiv.2608.05565"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.05565","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.05565","pdf_url":"https://arxiv.org/pdf/2608.05565","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":null,"license_id":null,"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/2608.05565","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129785631","display_name":"Feier Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Feier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133846446","display_name":"Wanke Xia","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Wanke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139248534","display_name":"Xu He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003681196","display_name":"Zilang Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zilang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5145999311","display_name":"Si Chen","orcid":"https://orcid.org/0009-0009-5842-8898","observed_orcids":["https://orcid.org/0009-0009-5842-8898"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Si","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129684689","display_name":"Dongxia Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Dongxia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125910817","display_name":"Liyang Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Liyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146053455","display_name":"Qimeng Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Qimeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121363469","display_name":"Zhengbo Zhang","orcid":"https://orcid.org/0009-0000-8956-0095","observed_orcids":["https://orcid.org/0009-0000-8956-0095"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhengbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138199680","display_name":"Wenming Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Wenming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121832101","display_name":"Zhiyong Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zhiyong","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":0.9984999895095825,"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":0.9984999895095825,"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":0.0003000000142492354,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00019999999494757503,"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/vision-language-models","display_name":"vision-language models","score":0.8009999990463257},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.5299999713897705},{"id":"https://openalex.org/keywords/cross-modal-reasoning","display_name":"cross-modal reasoning","score":0.7609999775886536},{"id":"https://openalex.org/keywords/spatiotemporal-coherence","display_name":"spatiotemporal coherence","score":0.7200000286102295}],"concepts":[{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.8162999749183655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914000153541565},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.708899974822998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6927000284194946},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6758000254631042},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.6129999756813049},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5611000061035156},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.2694000005722046},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.05565","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.05565","pdf_url":"https://arxiv.org/pdf/2608.05565","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.05565","doi":"https://doi.org/10.48550/arxiv.2608.05565","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.05565","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.05565","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.05565","pdf_url":"https://arxiv.org/pdf/2608.05565","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7139950550","https://openalex.org/W7148752390","https://openalex.org/W7162815581","https://openalex.org/W7077920225","https://openalex.org/W7148768444","https://openalex.org/W7123655772","https://openalex.org/W7203897790","https://openalex.org/W7223392028","https://openalex.org/W7134887511","https://openalex.org/W2965570359"],"abstract_inverted_index":{"Video":[0,75,100],"object":[1,9,120,191],"removal":[2,114,192],"must":[3],"eliminate":[4],"not":[5],"only":[6],"the":[7,83,99,129,163,181],"target":[8],"but":[10],"also":[11],"its":[12,185],"induced":[13],"effects":[14],"while":[15],"maintaining":[16],"high-fidelity":[17],"and":[18,33,56,92,109,116,122,149,173,180],"spatiotemporally":[19],"coherent":[20],"restoration.":[21],"Existing":[22],"methods":[23],"mainly":[24],"learn":[25],"object-effect":[26,104],"correspondences":[27],"implicitly":[28],"from":[29],"predefined":[30],"effect":[31],"categories":[32],"fixed":[34],"data":[35],"distributions,":[36],"limiting":[37],"their":[38],"generalization":[39],"to":[40,187],"complex":[41,146,194],"real-world":[42,133,195],"scenes":[43],"involving":[44],"compositional":[45],"effects,":[46,52,148],"spatially":[47],"detached":[48],"or":[49],"weakly":[50],"correlated":[51],"long-tail":[53],"physical":[54],"phenomena,":[55],"dynamically":[57],"evolving":[58,123],"interactions.":[59],"We":[60],"propose":[61],"EffectLearner,":[62],"a":[63,68,73,79,89,139,151],"semantic-reasoning-enhanced":[64],"framework":[65,130],"that":[66,155],"combines":[67,156],"VLM-based":[69],"Object-Effect":[70],"Reasoner":[71,84],"with":[72,159],"DiT-based":[74],"Eraser.":[76],"Guided":[77],"by":[78],"structured":[80],"effect-analysis":[81],"prompt,":[82],"performs":[85],"cross-modal":[86],"reasoning":[87],"over":[88],"target-highlighted":[90],"video":[91,141,190],"extracts":[93],"compact":[94],"effect-aware":[95],"context,":[96],"which":[97],"guides":[98],"Eraser":[101],"toward":[102],"comprehensive":[103],"removal.":[105],"Motion-aware":[106],"mask":[107],"guidance":[108],"motion-consistency":[110],"supervision":[111,158],"further":[112,136],"improve":[113],"coverage":[115],"spatiotemporal":[117],"stability":[118],"under":[119],"motion":[121],"scene":[124],"dynamics.":[125],"To":[126],"fully":[127],"exploit":[128],"in":[131,193],"challenging":[132,182],"scenarios,":[134],"we":[135],"construct":[137],"EffectWorld,":[138],"paired":[140],"dataset":[142],"specifically":[143],"designed":[144],"for":[145],"object-induced":[147],"introduce":[150],"progressive":[152],"training":[153],"curriculum":[154],"common":[157],"complex-effect":[160],"data.":[161],"On":[162],"standard":[164],"ROSE-Bench,":[165],"EffectLearner":[166],"outperforms":[167],"existing":[168],"baselines":[169],"on":[170,177],"most":[171],"metrics":[172],"achieves":[174],"clear":[175],"advantages":[176],"both":[178],"EffectWorld-Eval":[179],"EffectWorld-Wild,":[183],"demonstrating":[184],"ability":[186],"deliver":[188],"high-quality":[189],"scenes.":[196]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-08T00:00:00"}