{"id":"https://openalex.org/W7110151566","doi":"https://doi.org/10.1145/3757377.3763990","title":"CamPVG: Camera-Controlled Panoramic Video Generation with Epipolar-Aware Diffusion","display_name":"CamPVG: Camera-Controlled Panoramic Video Generation with Epipolar-Aware Diffusion","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7110151566","doi":"https://doi.org/10.1145/3757377.3763990"},"language":null,"primary_location":{"id":"doi:10.1145/3757377.3763990","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","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":null,"display_name":"Chenhao Ji","orcid":"https://orcid.org/0009-0005-6718-4582"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["CN","KY"],"is_corresponding":true,"raw_author_name":"Chenhao Ji","raw_affiliation_strings":["Tongji University, Shanghai, China and DAMO Academy, Alibaba group, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China and DAMO Academy, Alibaba group, Shanghai, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chaohui Yu","orcid":"https://orcid.org/0000-0002-7852-4491"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaohui Yu","raw_affiliation_strings":["DAMO Academy, Alibaba group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junyao Gao","orcid":"https://orcid.org/0009-0004-6527-8166"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyao Gao","raw_affiliation_strings":["Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fan Wang","orcid":"https://orcid.org/0000-0001-7320-1119"},"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"]},{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY","US"],"is_corresponding":false,"raw_author_name":"Fan Wang","raw_affiliation_strings":["DAMO Academy, Alibaba group, SunnyVale, USA"],"affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba group, SunnyVale, USA","institution_ids":["https://openalex.org/I4210086143","https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":null,"display_name":"Cairong Zhao","orcid":"https://orcid.org/0000-0001-6745-9674"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cairong Zhao","raw_affiliation_strings":["Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210086143","https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":2.7365,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91978827,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.20819999277591705,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.20819999277591705,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.20520000159740448,"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":0.13850000500679016,"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/epipolar-geometry","display_name":"Epipolar geometry","score":0.8371999859809875},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5188000202178955},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.459199994802475},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.44830000400543213},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43700000643730164},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4307999908924103},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.40939998626708984},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.40290001034736633},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.35040000081062317},{"id":"https://openalex.org/keywords/panorama","display_name":"Panorama","score":0.32899999618530273}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.8452000021934509},{"id":"https://openalex.org/C23379248","wikidata":"https://www.wikidata.org/wiki/Q200904","display_name":"Epipolar geometry","level":3,"score":0.8371999859809875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7922000288963318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7039999961853027},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36390000581741333},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C2780580889","wikidata":"https://www.wikidata.org/wiki/Q41363","display_name":"Panorama","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C2778852477","wikidata":"https://www.wikidata.org/wiki/Q313614","display_name":"Video camera","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C110898773","wikidata":"https://www.wikidata.org/wiki/Q2933935","display_name":"Camera resectioning","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C94816000","wikidata":"https://www.wikidata.org/wiki/Q5026006","display_name":"Camera auto-calibration","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C120515352","wikidata":"https://www.wikidata.org/wiki/Q2564580","display_name":"Image plane","level":3,"score":0.25279998779296875},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757377.3763990","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2471962767","https://openalex.org/W2962785568","https://openalex.org/W4214625308","https://openalex.org/W4309957684","https://openalex.org/W4310695675","https://openalex.org/W4312423208","https://openalex.org/W4312933868","https://openalex.org/W4388093548","https://openalex.org/W4389115686","https://openalex.org/W4393154594","https://openalex.org/W4393967358","https://openalex.org/W4395483753","https://openalex.org/W4396712913","https://openalex.org/W4399424705","https://openalex.org/W4399912905","https://openalex.org/W4400573519","https://openalex.org/W4402387301","https://openalex.org/W4402660110","https://openalex.org/W4402715862","https://openalex.org/W4402727274","https://openalex.org/W4402727736","https://openalex.org/W4403003238","https://openalex.org/W4404260636","https://openalex.org/W4405090792","https://openalex.org/W4413144818","https://openalex.org/W4413147273"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"camera-controlled":[1],"video":[2,13,26,32,65,177],"generation":[3,33,66],"has":[4],"seen":[5],"rapid":[6],"development,":[7],"offering":[8],"more":[9],"precise":[10,69],"control":[11,22],"over":[12],"generation.":[14,178],"However,":[15],"existing":[16,173],"methods":[17,116,174],"predominantly":[18],"focus":[19],"on":[20,85],"camera":[21,70,74,97,169],"in":[23,45,175],"perspective":[24],"projection":[25],"generation,":[27],"while":[28],"geometrically":[29],"consistent":[30,167],"panoramic":[31,46,64,78,92,109,155,165,176],"remains":[34],"challenging.":[35],"This":[36,104,140],"limitation":[37],"is":[38],"primarily":[39],"due":[40],"to":[41,119],"the":[42,59,112,149],"inherent":[43],"complexities":[44],"pose":[47,105],"representation":[48],"and":[49,80,151],"spherical":[50,86,101,126],"projection.":[51,87],"To":[52],"address":[53],"this":[54],"issue,":[55],"we":[56,89,123],"propose":[57,90],"CamPVG,":[58],"first":[60],"diffusion-based":[61],"framework":[62],"for":[63,77],"guided":[67],"by":[68],"poses.":[71],"We":[72],"achieve":[73],"position":[75],"encoding":[76],"images":[79],"cross-view":[81,144],"feature":[82,145],"aggregation":[83],"based":[84],"Specifically,":[88],"a":[91,125],"Pl\u00fccker":[93],"embedding":[94],"that":[95,129,160],"encodes":[96],"extrinsic":[98],"parameters":[99],"through":[100,133],"coordinate":[102],"transformation.":[103],"encoder":[106],"effectively":[107],"captures":[108],"geometry,":[110],"overcoming":[111],"limitations":[113],"of":[114,153],"traditional":[115],"when":[117],"applied":[118],"equirectangular":[120],"projections.":[121],"Additionally,":[122],"introduce":[124],"epipolar":[127,138],"module":[128,141],"enforces":[130],"geometric":[131],"constraints":[132],"adaptive":[134],"attention":[135],"masking":[136],"along":[137],"lines.":[139],"enables":[142],"fine-grained":[143],"aggregation,":[146],"substantially":[147],"enhancing":[148],"quality":[150],"consistency":[152],"generated":[154],"videos.":[156],"Extensive":[157],"experiments":[158],"demonstrate":[159],"our":[161],"method":[162],"generates":[163],"high-quality":[164],"videos":[166],"with":[168],"trajectories,":[170],"far":[171],"surpassing":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-08T00:00:00"}
