{"id":"https://openalex.org/W4385768093","doi":"https://doi.org/10.24963/ijcai.2023/167","title":"Learning 3D Photography Videos via Self-supervised Diffusion on Single Images","display_name":"Learning 3D Photography Videos via Self-supervised Diffusion on Single Images","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385768093","doi":"https://doi.org/10.24963/ijcai.2023/167"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/167","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/167","pdf_url":"https://www.ijcai.org/proceedings/2023/0167.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0167.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100382659","display_name":"Xiaodong Wang","orcid":"https://orcid.org/0000-0002-3299-616X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101571309","display_name":"Chenfei Wu","orcid":"https://orcid.org/0000-0002-5678-9691"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chenfei Wu","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101005060","display_name":"Shengming Yin","orcid":"https://orcid.org/0009-0003-7769-184X"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shengming Yin","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003777635","display_name":"Minheng Ni","orcid":"https://orcid.org/0000-0001-6483-0650"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Minheng Ni","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358523","display_name":"Jianfeng Wang","orcid":"https://orcid.org/0000-0003-0932-3060"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianfeng Wang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657555","display_name":"Linjie Li","orcid":"https://orcid.org/0000-0003-0867-8863"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Linjie Li","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050209478","display_name":"Zhengyuan Yang","orcid":"https://orcid.org/0000-0002-5808-0889"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhengyuan Yang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049191429","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-6844-2521"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436501","display_name":"Lijuan Wang","orcid":"https://orcid.org/0000-0002-2517-2728"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lijuan Wang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101728117","display_name":"Zicheng Liu","orcid":"https://orcid.org/0000-0001-5894-7828"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zicheng Liu","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088688674","display_name":"Yuejian Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Yuejian Fang","raw_affiliation_strings":["Peking University","Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042018181","display_name":"Nan Duan","orcid":"https://orcid.org/0000-0002-3387-4674"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nan Duan","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4855,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71949835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1506","last_page":"1514"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.8227565288543701},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.8149162530899048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7939451932907104},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7455554008483887},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.657593846321106},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5304312705993652},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.49226370453834534},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.48234862089157104},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43673276901245117},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3596896231174469},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.33106380701065063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8227565288543701},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.8149162530899048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7939451932907104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7455554008483887},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.657593846321106},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5304312705993652},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.49226370453834534},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.48234862089157104},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43673276901245117},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3596896231174469},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33106380701065063}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/167","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/167","pdf_url":"https://www.ijcai.org/proceedings/2023/0167.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/167","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/167","pdf_url":"https://www.ijcai.org/proceedings/2023/0167.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385768093.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2561196672","https://openalex.org/W2804091141","https://openalex.org/W2942368658","https://openalex.org/W2962785568","https://openalex.org/W2962974533","https://openalex.org/W2981017910","https://openalex.org/W2985299701","https://openalex.org/W3034528136","https://openalex.org/W3034801905","https://openalex.org/W3035524985","https://openalex.org/W3036167779","https://openalex.org/W3081167590","https://openalex.org/W3106333289","https://openalex.org/W3109234934","https://openalex.org/W3109585842","https://openalex.org/W3111114371","https://openalex.org/W3157199281","https://openalex.org/W3158252298","https://openalex.org/W3166396011","https://openalex.org/W3202343472","https://openalex.org/W3202407679","https://openalex.org/W3203828408","https://openalex.org/W3204568876","https://openalex.org/W3204789496","https://openalex.org/W4214868041","https://openalex.org/W4224035735","https://openalex.org/W4281485151","https://openalex.org/W4281563989","https://openalex.org/W4283388932","https://openalex.org/W4283805732","https://openalex.org/W4286588185","https://openalex.org/W4298185919","https://openalex.org/W4303441850","https://openalex.org/W4312816690","https://openalex.org/W4312933868","https://openalex.org/W4313169082"],"related_works":["https://openalex.org/W2380775572","https://openalex.org/W2213520135","https://openalex.org/W2244018504","https://openalex.org/W4242046654","https://openalex.org/W3174923100","https://openalex.org/W3134074939","https://openalex.org/W2117562399","https://openalex.org/W4298074124","https://openalex.org/W2587407424","https://openalex.org/W2371381961"],"abstract_inverted_index":{"3D":[0,11],"photography":[1],"renders":[2],"a":[3,7,48,71,81,88,131,154],"static":[4],"image":[5,95,99],"into":[6,141],"video":[8],"with":[9,30,100,179],"appealing":[10],"visual":[12],"effects.":[13],"Existing":[14],"approaches":[15],"typically":[16],"first":[17],"conduct":[18],"monocular":[19],"depth":[20],"estimation,":[21],"then":[22],"render":[23],"the":[24,64,77,92,97,112,116,126,142,146,160],"input":[25,83,165],"frame":[26],"to":[27,39,111],"subsequent":[28],"frames":[29],"various":[31],"viewpoints,":[32],"and":[33,66,96,144,162],"finally":[34],"use":[35,124],"an":[36],"inpainting":[37,45,78],"model":[38,46,75],"fill":[40],"those":[41],"missing/occluded":[42],"regions.":[43],"The":[44,104],"plays":[47],"crucial":[49],"role":[50],"in":[51],"rendering":[52],"quality,":[53],"but":[54],"it":[55],"is":[56],"normally":[57],"trained":[58],"on":[59,169],"out-of-domain":[60],"data.":[61],"To":[62,121],"reduce":[63],"training":[65,89,106],"inference":[67],"gap,":[68],"we":[69,85,129,152],"propose":[70],"novel":[72,155],"self-supervised":[73],"diffusion":[74],"as":[76],"module.":[79],"Given":[80],"single":[82],"image,":[84],"automatically":[86],"construct":[87],"pair":[90],"of":[91,125,164],"masked":[93,127],"occluded":[94],"ground-truth":[98],"random":[101],"cycle":[102],"rendering.":[103],"constructed":[105],"samples":[107],"are":[108],"closely":[109],"aligned":[110],"testing":[113],"instances,":[114],"without":[115],"need":[117],"for":[118],"data":[119],"annotation.":[120],"make":[122],"full":[123],"images,":[128],"designed":[130],"Masked":[132],"Enhanced":[133],"Block":[134],"(MEB),":[135],"which":[136,158],"can":[137],"be":[138],"easily":[139],"plugged":[140],"UNet":[143],"enhance":[145],"semantic":[147],"conditions.":[148],"Towards":[149],"real-world":[150],"animation,":[151],"present":[153],"task:":[156],"out-animation,":[157],"extends":[159],"space":[161],"time":[163],"objects.":[166],"Extensive":[167],"experiments":[168],"real":[170],"datasets":[171],"show":[172],"that":[173],"our":[174],"method":[175],"achieves":[176],"competitive":[177],"results":[178],"existing":[180],"SOTA":[181],"methods.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}