{"id":"https://openalex.org/W4417082420","doi":"https://doi.org/10.1109/iccv51701.2025.02384","title":"Autoscape: Geometry-Consistent Long-Horizon Scene Generation","display_name":"Autoscape: Geometry-Consistent Long-Horizon Scene Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417082420","doi":"https://doi.org/10.1109/iccv51701.2025.02384"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.02384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.20726","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019324790","display_name":"Jiacheng Chen","orcid":"https://orcid.org/0000-0001-6689-3647"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Jiacheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110045865","display_name":"Ziyu Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Ziyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086774067","display_name":"Mingfu Liang","orcid":"https://orcid.org/0000-0001-6779-2418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Mingfu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037811979","display_name":"Bingbing Zhuang","orcid":"https://orcid.org/0000-0002-2317-3882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Bingbing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046487166","display_name":"Jong-Chyi Su","orcid":"https://orcid.org/0000-0002-7933-8308"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Jong-Chyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002261892","display_name":"Sparsh Garg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garg, Sparsh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086721790","display_name":"Ying Wu","orcid":"https://orcid.org/0000-0001-6719-0855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Ying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046609009","display_name":"Manmohan Chandraker","orcid":"https://orcid.org/0000-0003-4683-2454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chandraker, Manmohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5019324790"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37377464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25700","last_page":"25711"},"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":0.7286999821662903,"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":0.7286999821662903,"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":0.09589999914169312,"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"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.05900000035762787,"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/process","display_name":"Process (computing)","score":0.5407000184059143},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4657000005245209},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4226999878883362},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.3840000033378601},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3605000078678131},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3158000111579895}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7706999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6850000023841858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6306999921798706},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3962000012397766},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3840000033378601},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3158000111579895},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28349998593330383},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.2614000141620636}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.20726","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.20726","pdf_url":"https://arxiv.org/pdf/2510.20726","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},{"id":"doi:10.48550/arxiv.2510.20726","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.20726","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.20726","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.20726","pdf_url":"https://arxiv.org/pdf/2510.20726","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"AutoScape,":[3],"a":[4,14,50,77,84],"long-horizon":[5,113],"driving":[6,105],"scene":[7,60],"generation":[8],"framework.":[9],"At":[10],"its":[11],"core":[12],"is":[13],"novel":[15],"RGB-D":[16,82],"diffusion":[17,86],"model":[18,42,87],"that":[19],"iteratively":[20],"generates":[21,100],"sparse,":[22],"geometrically":[23,103],"consistent":[24,104],"keyframes,":[25,69,83],"serving":[26],"as":[27],"reliable":[28],"anchors":[29],"for":[30],"the":[31,41,58,73,112,119],"scene's":[32],"appearance":[33],"and":[34,47,70,95,102,115,124],"geometry.":[35],"To":[36],"maintain":[37],"long-range":[38],"geometric":[39],"consistency,":[40],"1)":[43],"jointly":[44],"handles":[45],"image":[46],"depth":[48],"in":[49],"shared":[51],"latent":[52],"space,":[53],"2)":[54],"explicitly":[55],"conditions":[56],"on":[57],"existing":[59],"geometry":[61],"(i.e.,":[62],"rendered":[63],"point":[64],"clouds)":[65],"from":[66],"previously":[67],"generated":[68],"3)":[71],"steers":[72],"sampling":[74],"process":[75],"with":[76],"warp-consistent":[78],"guidance.":[79],"Given":[80],"high-quality":[81],"video":[85,97],"then":[88],"interpolates":[89],"between":[90],"them":[91],"to":[92],"produce":[93],"dense":[94],"coherent":[96],"frames.":[98],"AutoScape":[99],"realistic":[101],"videos":[106],"of":[107],"over":[108,118],"20":[109],"seconds,":[110],"improving":[111],"FID":[114],"FVD":[116],"scores":[117],"prior":[120],"state-of-the-art":[121],"by":[122],"48.6\\%":[123],"43.0\\%,":[125],"respectively.":[126]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-25T00:00:00"}