{"id":"https://openalex.org/W4408353005","doi":"https://doi.org/10.1109/icassp49660.2025.10889873","title":"TransVDM: Motion-Constrained Video Diffusion Model for Transparent Video Synthesis","display_name":"TransVDM: Motion-Constrained Video Diffusion Model for Transparent Video Synthesis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353005","doi":"https://doi.org/10.1109/icassp49660.2025.10889873"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5066398844","display_name":"Menghao Li","orcid":"https://orcid.org/0000-0003-2051-3690"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Menghao Li","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenghao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenghao Zhang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113346173","display_name":"Junchao Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junchao Liao","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059332762","display_name":"Long Qin","orcid":"https://orcid.org/0000-0002-4508-1663"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Long Qin","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062260595","display_name":"Weizhi Wang","orcid":"https://orcid.org/0000-0002-7310-4068"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weizhi Wang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066398844"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03179661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9977999925613403,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9977999925613403,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/computer-science","display_name":"Computer science","score":0.6924647092819214},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5266815423965454},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5234719514846802},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5099514722824097},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48297348618507385},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.454872727394104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34462326765060425},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07113650441169739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6924647092819214},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5266815423965454},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5234719514846802},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5099514722824097},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48297348618507385},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.454872727394104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34462326765060425},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07113650441169739},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2112796928","https://openalex.org/W2889986507","https://openalex.org/W2963092440","https://openalex.org/W2964245526","https://openalex.org/W4294541506","https://openalex.org/W4385764500","https://openalex.org/W4390872297","https://openalex.org/W4400819434","https://openalex.org/W6753914649","https://openalex.org/W6809935361","https://openalex.org/W6810793953","https://openalex.org/W6810940779","https://openalex.org/W6811072154","https://openalex.org/W6838785959","https://openalex.org/W6844305113","https://openalex.org/W6845281891","https://openalex.org/W6846959760","https://openalex.org/W6855459923","https://openalex.org/W6855803553","https://openalex.org/W6858865347","https://openalex.org/W6870839691"],"related_works":["https://openalex.org/W1570573051","https://openalex.org/W4386051551","https://openalex.org/W2755342338","https://openalex.org/W1842208754","https://openalex.org/W2779427294","https://openalex.org/W2032145508","https://openalex.org/W2725946685","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2102886119"],"abstract_inverted_index":{"Recent":[0],"developments":[1],"in":[2],"Video":[3],"Diffusion":[4],"Models":[5],"(VDMs)":[6],"have":[7],"demonstrated":[8],"remarkable":[9],"capability":[10],"to":[11,89,113],"generate":[12],"high-quality":[13],"video":[14,42,73,91],"content.":[15],"Nonetheless,":[16],"the":[17,34,68,79,83,96,101,107,110,131],"potential":[18],"of":[19,72,82,98,133],"VDMs":[20],"for":[21,40,126],"creating":[22],"transparent":[23,41,90,99,124],"videos":[24],"remains":[25],"largely":[26],"uncharted.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31,118],"introduce":[32],"TransVDM,":[33],"first":[35],"diffusion-based":[36],"model":[37],"specifically":[38],"designed":[39],"generation.":[43],"TransVDM":[44],"integrates":[45,103],"a":[46,52,58,86,120],"Transparent":[47],"Variational":[48],"Autoencoder":[49],"(TVAE)":[50],"and":[51,75],"pretrained":[53],"UNet-based":[54],"VDM,":[55,111],"along":[56],"with":[57],"novel":[59],"Alpha":[60],"Motion":[61],"Constraint":[62],"Module":[63],"(AMCM).":[64],"The":[65],"TVAE":[66],"captures":[67],"alpha":[69],"channel":[70],"transparency":[71],"frames":[74,125],"encodes":[76],"it":[77],"into":[78],"latent":[80],"space":[81],"VDMs,":[84],"facilitating":[85],"seamless":[87],"transition":[88],"diffusion":[92],"models.":[93],"To":[94],"improve":[95],"detection":[97],"areas,":[100],"AMCM":[102],"motion":[104],"constraints":[105],"from":[106],"foreground":[108],"within":[109],"helping":[112],"reduce":[114],"undesirable":[115],"artifacts.":[116],"Moreover,":[117],"curate":[119],"dataset":[121],"containing":[122],"250K":[123],"training.":[127],"Experimental":[128],"results":[129],"demonstrate":[130],"effectiveness":[132],"our":[134],"approach":[135],"across":[136],"various":[137],"benchmarks.":[138]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
