{"id":"https://openalex.org/W7118162100","doi":"https://doi.org/10.1109/tmm.2026.3651030","title":"DreamJourney: Perpetual View Generation With Video Diffusion Models","display_name":"DreamJourney: Perpetual View Generation With Video Diffusion Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7118162100","doi":"https://doi.org/10.1109/tmm.2026.3651030"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651030","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5121968348","display_name":"Bo Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Pan","raw_affiliation_strings":["State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-4561-2469","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121917968","display_name":"Yang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Chen","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-9058-5051","affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094255763","display_name":"Yingwei Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingwei Pan","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4344-8898","affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121921285","display_name":"Ting Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7587-101X","affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001088173","display_name":"W. Y. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8365-4741","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5094255766","display_name":"Tao Mei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2497-7732","affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5121968348"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01855026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"2578","last_page":"2592"},"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":0.9491000175476074,"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":0.9491000175476074,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.016599999740719795,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.003599999938160181,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5357000231742859},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5175999999046326},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47269999980926514},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4296000003814697},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.40119999647140503},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.38850000500679016},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3767000138759613},{"id":"https://openalex.org/keywords/single-camera","display_name":"Single camera","score":0.35659998655319214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8684999942779541},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7329000234603882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6693999767303467},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5357000231742859},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5175999999046326},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.40119999647140503},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C3018868555","wikidata":"https://www.wikidata.org/wiki/Q2918907","display_name":"Single camera","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C185078393","wikidata":"https://www.wikidata.org/wiki/Q313783","display_name":"Stereo camera","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651030","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G163158741","display_name":null,"funder_award_id":"20240484681","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G3405827317","display_name":null,"funder_award_id":"62421003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3645435832","display_name":null,"funder_award_id":"U22B2034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Perpetual":[0],"view":[1,102,184,226,241],"generation":[2,103,190],"aims":[3],"to":[4,10,30,59,67,96,122,148,166,186,207,223],"synthesize":[5,31],"a":[6,17,25,83,98,128,134,161,202,209],"long-term":[7],"video":[8,93,139,164,220],"corresponding":[9],"an":[11],"arbitrary":[12],"camera":[13,39,107,136,171],"trajectory":[14],"solely":[15],"from":[16,133],"single":[18],"input":[19,120],"image.":[20],"Recent":[21],"methods":[22,253],"commonly":[23],"utilize":[24],"pre-trained":[26],"text-to-image":[27],"diffusion":[28,45,94,140,221],"model":[29,46,141,206,222],"new":[32,99],"content":[33],"of":[34,62,92,130,248],"previously":[35],"unseen":[36],"regions":[37,152],"along":[38],"movement.":[40],"However,":[41],"the":[42,72,88,119,150,158,167,189,246],"underlying":[43],"2D":[44],"lacks":[47],"3D":[48,64,123,168],"awareness":[49],"and":[50,109,126,153,170,183,192,218,232,256],"results":[51],"in":[52,113,197,215],"distorted":[53],"artifacts.":[54],"Moreover,":[55],"they":[56],"are":[57,234],"limited":[58],"generating":[60],"views":[61],"static":[63],"scenes,":[65],"neglecting":[66],"capture":[68],"object":[69,110,213,228],"movements":[70,108,214],"within":[71],"dynamic":[73,239],"4D":[74],"world.":[75],"To":[76],"alleviate":[77],"these":[78],"issues,":[79],"we":[80,174],"present":[81],"DreamJourney,":[82],"two-stage":[84],"framework":[85],"that":[86],"leverages":[87,201],"world":[89],"simulation":[90],"capacity":[91],"models":[95],"trigger":[97],"perpetual":[100,238],"scene":[101,169,240],"task":[104],"with":[105,227],"both":[106,254],"dynamics.":[111],"Specifically,":[112],"stage":[114,198],"I,":[115],"DreamJourney":[116,200,250],"first":[117],"lifts":[118],"image":[121],"point":[124],"cloud":[125],"renders":[127],"sequence":[129],"partial":[131],"images":[132],"specific":[135],"trajectory.":[137,172],"A":[138],"is":[142],"then":[143],"utilized":[144],"as":[145],"generative":[146],"prior":[147],"complete":[149],"missing":[151],"enhance":[154],"visual":[155,194],"coherence":[156],"across":[157],"sequence,":[159],"producing":[160],"cross-view":[162],"consistent":[163],"adheres":[165],"Meanwhile,":[173],"introduce":[175],"two":[176],"simple":[177],"yet":[178],"effective":[179],"strategies":[180],"(early":[181],"stopping":[182],"padding)":[185],"further":[187],"stabilize":[188],"process":[191],"improve":[193],"quality.":[195],"Next,":[196],"II,":[199],"multimodal":[203],"large":[204],"language":[205],"produce":[208],"text":[210],"prompt":[211],"describing":[212],"current":[216,225],"view,":[217],"uses":[219],"animate":[224],"movements.":[229],"Stage":[230],"I":[231],"II":[233],"repeated":[235],"recurrently,":[236],"enabling":[237],"generation.":[242],"Extensive":[243],"experiments":[244],"demonstrate":[245],"superiority":[247],"our":[249],"over":[251],"state-of-the-art":[252],"quantitatively":[255],"qualitatively.":[257],"Our":[258],"project":[259],"page:":[260],"<uri":[261],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[262],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://dream-journey.vercel.app/</uri>.":[263]},"counts_by_year":[],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2026-01-05T00:00:00"}
