{"id":"https://openalex.org/W6967042002","doi":"https://doi.org/10.48550/arxiv.2508.10688","title":"Novel View Synthesis using DDIM Inversion","display_name":"Novel View Synthesis using DDIM Inversion","publication_year":2025,"publication_date":"2025-08-14","ids":{"openalex":"https://openalex.org/W6967042002","doi":"https://doi.org/10.48550/arxiv.2508.10688"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.10688","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.10688","pdf_url":"https://arxiv.org/pdf/2508.10688","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.10688","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Singh, Sehajdeep","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singh, Sehajdeep","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Subramanyam, A V","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Subramanyam, A V","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gupta, Aditya","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gupta, Aditya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Gupta, Sahil","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gupta, Sahil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9458000063896179,"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":0.9458000063896179,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.025699999183416367,"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":0.024000000208616257,"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/novel-view-synthesis","display_name":"novel view synthesis","score":0.9559999704360962},{"id":"https://openalex.org/keywords/ddim-inversion","display_name":"DDIM inversion","score":0.9549999833106995},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.7089999914169312},{"id":"https://openalex.org/keywords/noise-correlation","display_name":"noise correlation","score":0.6460000276565552},{"id":"https://openalex.org/keywords/single-view-3d-reconstruction","display_name":"single-image 3D reconstruction","score":0.6510000228881836},{"id":"https://openalex.org/keywords/geometric-consistency","display_name":"geometric consistency","score":0.44200000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160000205039978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6524999737739563},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5422000288963318},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5357000231742859},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49900001287460327},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.46889999508857727},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4309999942779541},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.3765999972820282},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.32350000739097595},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.3116999864578247},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.3093000054359436},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.10688","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.10688","pdf_url":"https://arxiv.org/pdf/2508.10688","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2508.10688","doi":"https://doi.org/10.48550/arxiv.2508.10688","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.10688","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.10688","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.10688","pdf_url":"https://arxiv.org/pdf/2508.10688","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/1","score":0.6527823209762573,"display_name":"No poverty"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Single-image":[0],"novel":[1,175],"view":[2,115,176],"synthesis":[3],"requires":[4],"viewpoint-dependent":[5],"structural":[6,45,160],"changes":[7],"while":[8,108],"retaining":[9],"source-scene":[10],"information":[11],"and":[12,47,77,129,162],"inferring":[13],"unobserved":[14],"content.":[15],"We":[16,67],"formulate":[17],"this":[18],"task":[19],"as":[20,165],"a":[21,26,44,48,70,82,122,166],"camera-conditioned":[22],"initialization":[23,143,164],"problem":[24],"for":[25,174],"frozen":[27,89,171],"pretrained":[28,110],"latent":[29],"diffusion":[30,172],"model.":[31],"At":[32],"an":[33],"intermediate":[34],"DDIM":[35,102],"inversion":[36],"timestep,":[37],"we":[38],"decompose":[39],"the":[40,60,64,74,88,97,109,113,141],"source":[41,49,65,78],"representation":[42],"into":[43],"mean":[46,62,76,99],"noise":[50,79,92],"residual.":[51],"A":[52],"pose-conditioned":[53],"translation":[54,161],"U-Net":[55],"(TUNet)":[56],"learns":[57],"to":[58,100,148,169],"predict":[59],"target-view":[61],"from":[63],"mean.":[66],"then":[68],"introduce":[69],"score-guided":[71],"fusion":[72],"strategy:":[73],"predicted":[75],"residual":[80],"form":[81],"proposal":[83],"that":[84,140],"is":[85,94,106],"evaluated":[86],"by":[87],"denoiser,":[90],"whose":[91],"prediction":[93],"combined":[95],"with":[96],"translated":[98],"initialize":[101],"sampling.":[103],"Only":[104],"TUNet":[105],"trained,":[107],"model":[111],"synthesizes":[112],"final":[114],"without":[116],"explicit":[117],"reconstruction":[118],"or":[119],"rendering":[120],"of":[121,150],"shared":[123],"3D":[124],"scene.":[125],"Experiments":[126],"on":[127],"MVImgNet":[128],"RealEstate10K":[130],"demonstrate":[131],"competitive":[132],"performance.":[133],"Beyond":[134],"image-level":[135],"metrics,":[136],"Wasserstein":[137],"comparisons":[138],"show":[139],"corrected":[142],"yields":[144],"trajectory-curvature":[145],"distributions":[146],"closer":[147],"those":[149],"ground-truth":[151],"target-initialized":[152],"sampling":[153],"than":[154],"raw":[155],"fusion.":[156],"These":[157],"results":[158],"support":[159],"source-conditioned":[163],"practical":[167],"approach":[168],"reusing":[170],"priors":[173],"synthesis.":[177]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}