{"id":"https://openalex.org/W4415540453","doi":"https://doi.org/10.1145/3746027.3754779","title":"Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion","display_name":"Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540453","doi":"https://doi.org/10.1145/3746027.3754779"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754779","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754779","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754779","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089529572","display_name":"Xueyang Kang","orcid":"https://orcid.org/0000-0001-7159-676X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xueyang Kang","raw_affiliation_strings":["University of Melbourne, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7159-676X","affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113750451","display_name":"Zhengkang Xiang","orcid":"https://orcid.org/0009-0005-8322-8696"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhengkang Xiang","raw_affiliation_strings":["University of Melbourne, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0009-0005-8322-8696","affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083880559","display_name":"Zezheng Zhang","orcid":"https://orcid.org/0000-0002-2853-7729"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zezheng Zhang","raw_affiliation_strings":["University of Melbourne, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2853-7729","affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003580485","display_name":"Kourosh Khoshelham","orcid":"https://orcid.org/0000-0001-6639-1727"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kourosh Khoshelham","raw_affiliation_strings":["University of Melbourne, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6639-1727","affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165779595"],"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":"9375","last_page":"9384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":1.0,"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":1.0,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9994000196456909,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9973999857902527,"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/panorama","display_name":"Panorama","score":0.8815000057220459},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.7003999948501587},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5170999765396118},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5162000060081482},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.4867999851703644},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.4675000011920929},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46369999647140503},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.45660001039505005}],"concepts":[{"id":"https://openalex.org/C2780580889","wikidata":"https://www.wikidata.org/wiki/Q41363","display_name":"Panorama","level":2,"score":0.8815000057220459},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7872999906539917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7142000198364258},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7003999948501587},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.4675000011920929},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46369999647140503},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.45660001039505005},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.33340001106262207},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754779","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754779","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.00843","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.00843","pdf_url":"https://arxiv.org/pdf/2509.00843","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754779","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754779","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2904829482","https://openalex.org/W2949258649","https://openalex.org/W2962785568","https://openalex.org/W2964251418","https://openalex.org/W2964339842","https://openalex.org/W3009928773","https://openalex.org/W4225793068","https://openalex.org/W4312324876","https://openalex.org/W4312623579","https://openalex.org/W4386065887","https://openalex.org/W4386076653","https://openalex.org/W4390872297","https://openalex.org/W4390872556","https://openalex.org/W4390873135","https://openalex.org/W4390874580","https://openalex.org/W4394597526","https://openalex.org/W4402727155","https://openalex.org/W4402727736","https://openalex.org/W4412587627"],"related_works":[],"abstract_inverted_index":{"Novel":[0],"view":[1,45,71,77],"synthesis":[2],"(NVS)":[3],"from":[4,22,88,105,117],"a":[5,54,64,89,97,126,136],"single":[6],"image":[7],"is":[8,186],"highly":[9],"ill-posed":[10],"due":[11],"to":[12,40,143],"large":[13],"unobserved":[14],"regions,":[15],"especially":[16],"for":[17],"views":[18,134,152,180],"that":[19,56,171],"deviate":[20],"significantly":[21],"the":[23,32,94,102,106,118],"input.":[24],"While":[25],"existing":[26,175],"methods":[27,176],"focus":[28],"on":[29,83,166],"consistency":[30,80],"between":[31],"source":[33],"and":[34,43,78,86,115,120],"generated":[35,90],"views,":[36],"they":[37],"often":[38],"fail":[39],"maintain":[41],"coherence":[42],"correct":[44],"alignment":[46],"across":[47],"long-range":[48],"or":[49],"looped":[50],"trajectories.":[51,183],"We":[52],"propose":[53],"model":[55,100],"addresses":[57],"this":[58],"by":[59,69,81],"decomposing":[60],"single-view":[61],"NVS":[62],"into":[63],"360-degree":[65],"scene":[66,79,103,168],"extrapolation":[67],"followed":[68],"novel":[70,133,151],"interpolation.":[72],"This":[73],"design":[74],"ensures":[75],"long-term":[76],"conditioning":[82],"keyframes":[84,111],"extracted":[85],"warped":[87,116],"panoramic":[91],"representation.":[92],"In":[93],"first":[95],"stage,":[96],"panorama":[98,119],"diffusion":[99,129,140],"learns":[101],"prior":[104,144],"input":[107],"perspective":[108],"image.":[109],"Perspective":[110],"are":[112],"then":[113],"sampled":[114],"used":[121],"as":[122],"anchor":[123],"frames":[124],"in":[125,155,177],"pre-trained":[127],"video":[128],"model,":[130],"which":[131],"generates":[132],"through":[135],"proposed":[137],"spatial":[138],"noise":[139],"process.":[141],"Compared":[142],"work,":[145],"our":[146,172],"method":[147],"produces":[148],"globally":[149],"consistent":[150],"--":[153,159],"even":[154],"loop":[156],"closure":[157],"scenarios":[158],"while":[160],"enabling":[161],"flexible":[162],"camera":[163],"control.":[164],"Experiments":[165],"diverse":[167],"datasets":[169],"demonstrate":[170],"approach":[173],"outperforms":[174],"generating":[178],"coherent":[179],"along":[181],"user-defined":[182],"Our":[184],"implementation":[185],"available":[187],"at":[188],"https://github.com/YiGuYT/LookBeyond.":[189]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
