SPARF: Neural Radiance Fields from Sparse and Noisy Poses
Neural Radiance Field (NeRF) has recently emerged as a powerful representation to synthesize photorealistic novel views. While showing impressive performance, it relies on the availability of dense input views with highly accurate camera poses, thus limiting its application in real-world scenarios....
Uloženo v:
| Vydáno v: | Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 4190 - 4200 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
01.06.2023
|
| Témata: | |
| ISSN: | 1063-6919 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Neural Radiance Field (NeRF) has recently emerged as a powerful representation to synthesize photorealistic novel views. While showing impressive performance, it relies on the availability of dense input views with highly accurate camera poses, thus limiting its application in real-world scenarios. In this work, we introduce Sparse Pose Adjusting Radiance Field (SPARF), to address the challenge of novel-view synthesis given only few wide-baseline input images (as low as 3) with noisy camera poses. Our approach exploits multi-view geometry constraints in order to jointly learn the NeRF and refine the camera poses. By relying on pixel matches extracted between the input views, our multiview correspondence objective enforces the optimized scene and camera poses to converge to a global and geometrically accurate solution. Our depth consistency loss further encourages the reconstructed scene to be consistent from any viewpoint. Our approach sets a new state of the art in the sparse-view regime on multiple challenging datasets. |
|---|---|
| AbstractList | Neural Radiance Field (NeRF) has recently emerged as a powerful representation to synthesize photorealistic novel views. While showing impressive performance, it relies on the availability of dense input views with highly accurate camera poses, thus limiting its application in real-world scenarios. In this work, we introduce Sparse Pose Adjusting Radiance Field (SPARF), to address the challenge of novel-view synthesis given only few wide-baseline input images (as low as 3) with noisy camera poses. Our approach exploits multi-view geometry constraints in order to jointly learn the NeRF and refine the camera poses. By relying on pixel matches extracted between the input views, our multiview correspondence objective enforces the optimized scene and camera poses to converge to a global and geometrically accurate solution. Our depth consistency loss further encourages the reconstructed scene to be consistent from any viewpoint. Our approach sets a new state of the art in the sparse-view regime on multiple challenging datasets. |
| Author | Rakotosaona, Marie-Julie Tombari, Federico Manhardt, Fabian Truong, Prune |
| Author_xml | – sequence: 1 givenname: Prune surname: Truong fullname: Truong, Prune email: prune.truong@vision.ee.ethz.ch organization: ETH Zurich – sequence: 2 givenname: Marie-Julie surname: Rakotosaona fullname: Rakotosaona, Marie-Julie email: mrakotosaona@google.com organization: Google – sequence: 3 givenname: Fabian surname: Manhardt fullname: Manhardt, Fabian email: fabianmanhardt@google.com organization: Google – sequence: 4 givenname: Federico surname: Tombari fullname: Tombari, Federico email: tombari@google.com organization: Google |
| BookMark | eNotzM1Kw0AUQOFRFKw1b9DFvEDinZ9MMu5KMFUoNaTqttx07sBImpSMLvr2BnR1Nofvnt0M40CMrQRkQoB9rD6bNpeFtJkEqTIADeUVS2xhS5WDAiFtec0WAoxKjRX2jiUxfgGAkkIYWy6Y3Tfrtn7iO_qZsOctuoDDkXgdqHeR-2k88f0Zp0gcB8d3Y4gX3oyR4gO79dhHSv67ZB_183v1km7fNq_VepsGCfo7RXSyFAbJdcaT94IQ0IDyRWG01yovjNHu2FFHWun5Eho9FNB1ttPeabVkqz83ENHhPIUTTpeDgFmfXfULWwdKBA |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/CVPR52729.2023.00408 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences |
| EISBN | 9798350301298 |
| EISSN | 1063-6919 |
| EndPage | 4200 |
| ExternalDocumentID | 10204816 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IH 6IL 6IN AAWTH ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP OCL RIE RIL RIO |
| ID | FETCH-LOGICAL-i204t-aad2816aedb6feff1ea0a603f7764f4357664dcbebe434edb14af070bb9b4fd43 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 81 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001058542604051&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 27 02:56:33 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i204t-aad2816aedb6feff1ea0a603f7764f4357664dcbebe434edb14af070bb9b4fd43 |
| PageCount | 11 |
| ParticipantIDs | ieee_primary_10204816 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-June |
| PublicationDateYYYYMMDD | 2023-06-01 |
| PublicationDate_xml | – month: 06 year: 2023 text: 2023-June |
| PublicationDecade | 2020 |
| PublicationTitle | Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) |
| PublicationTitleAbbrev | CVPR |
| PublicationYear | 2023 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0003211698 |
| Score | 2.6295917 |
| Snippet | Neural Radiance Field (NeRF) has recently emerged as a powerful representation to synthesize photorealistic novel views. While showing impressive performance,... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 4190 |
| SubjectTerms | Cameras Computer vision Geometry Image and video synthesis and generation Limiting Pattern recognition Rendering (computer graphics) Training |
| Title | SPARF: Neural Radiance Fields from Sparse and Noisy Poses |
| URI | https://ieeexplore.ieee.org/document/10204816 |
| WOSCitedRecordID | wos001058542604051&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA62ePBUHxXf5OB166bJ5uFNiosHKUur0lvJJhMoyG7ptoL_3iRdKx48eAshIWEmQ2aS-b5B6FY6ktLMuSRVxiaMU5NIyCAhRjBNpWaWRKDwsxiP5WymihasHrEwABCTz2AQmvEv39ZmE57KvIUHmlnCO6gjhNiCtXYPKtSHMlzJFh5HUnU3eism2dB7j4NQI3wQzqv8VUQl3iF575-rH6L-DxoPF7t75gjtQXWMeq37iFvjbE6QmhYPk_weB74N_Y4nkXXAz81DklqDA5AET5c-kAWsK4vH9aL5xEXdQNNHr_njy-gpaSsjJAu_h3WitR36nWgIIDpwjoBONU-pE4Iz5z0gwTmzpvQaYpT5UYRp5427LFXJnGX0FHWruoIzhJ3lQxDW-cGCKWKkygJtl48jrHUypeeoH0QxX27JL-bfUrj4o_8SHQRpb7OprlB3vdrANdo3H-tFs7qJKvsCWoaXEQ |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFH_oFPQ0PyZ-m4PXzqZJ08SbDMvEWco2ZbeRNgkMpB3rJvjfm3R14sGDtxASEt7LI-8l7_d7ALfcYJ-Exni-yJVHGck9rkPt4TyiknBJFa6BwoMoSfhkItIGrF5jYbTWdfKZ7rpm_ZevynzlnsqshTuaWcy2YSekNMBruNbmSYXYYIYJ3gDksC_uem_pMAys_9h1VcK77sTyX2VU6lskbv9z_QPo_ODxULq5aQ5hSxdH0G4cSNSYZ3UMYpQ-DON75Bg35Dsa1rwDdm7s0tQq5KAkaDS3oaxGslAoKWfVJ0rLSlcdeI0fx72-19RG8GZ2D0tPShXYnUjtYHTaGKylL5lPTBQxaqwPFDFGVZ5ZHVFC7ShMpbHmnWUio0ZRcgKtoiz0KSCjWKAjZezgiAqccxE64i4bSShluE_OoONEMZ2v6S-m31I4_6P_Bvb645fBdPCUPF_AvpP8OrfqElrLxUpfwW7-sZxVi-tafV9ouZpY |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=SPARF%3A+Neural+Radiance+Fields+from+Sparse+and+Noisy+Poses&rft.au=Truong%2C+Prune&rft.au=Rakotosaona%2C+Marie-Julie&rft.au=Manhardt%2C+Fabian&rft.au=Tombari%2C+Federico&rft.date=2023-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=4190&rft.epage=4200&rft_id=info:doi/10.1109%2FCVPR52729.2023.00408&rft.externalDocID=10204816 |