Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204752575> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W3204752575 endingPage "5751" @default.
- W3204752575 startingPage "5741" @default.
- W3204752575 abstract "Neural Radiance Fields (NeRF) have recently gained a surge of interest within the computer vision community for its power to synthesize photorealistic novel views of real-world scenes. One limitation of NeRF, however, is its requirement of accurate camera poses to learn the scene representations. In this paper, we propose Bundle-Adjusting Neural Radiance Fields (BARF) for training NeRF from imperfect (or even unknown) camera poses -- the joint problem of learning neural 3D representations and registering camera frames. We establish a theoretical connection to classical image alignment and show that coarse-to-fine registration is also applicable to NeRF. Furthermore, we show that naively applying positional encoding in NeRF has a negative impact on registration with a synthesis-based objective. Experiments on synthetic and real-world data show that BARF can effectively optimize the neural scene representations and resolve large camera pose misalignment at the same time. This enables view synthesis and localization of video sequences from unknown camera poses, opening up new avenues for visual localization systems (e.g. SLAM) and potential applications for dense 3D mapping and reconstruction." @default.
- W3204752575 created "2021-10-11" @default.
- W3204752575 creator A5037547726 @default.
- W3204752575 creator A5055053078 @default.
- W3204752575 creator A5067998833 @default.
- W3204752575 creator A5085020955 @default.
- W3204752575 date "2021-04-13" @default.
- W3204752575 modified "2023-09-24" @default.
- W3204752575 title "BARF: Bundle-Adjusting Neural Radiance Fields" @default.
- W3204752575 hasPublicationYear "2021" @default.
- W3204752575 type Work @default.
- W3204752575 sameAs 3204752575 @default.
- W3204752575 citedByCount "10" @default.
- W3204752575 countsByYear W32047525752021 @default.
- W3204752575 crossrefType "proceedings-article" @default.
- W3204752575 hasAuthorship W3204752575A5037547726 @default.
- W3204752575 hasAuthorship W3204752575A5055053078 @default.
- W3204752575 hasAuthorship W3204752575A5067998833 @default.
- W3204752575 hasAuthorship W3204752575A5085020955 @default.
- W3204752575 hasConcept C115961682 @default.
- W3204752575 hasConcept C120665830 @default.
- W3204752575 hasConcept C121332964 @default.
- W3204752575 hasConcept C154945302 @default.
- W3204752575 hasConcept C159985019 @default.
- W3204752575 hasConcept C179458375 @default.
- W3204752575 hasConcept C192562407 @default.
- W3204752575 hasConcept C23690007 @default.
- W3204752575 hasConcept C2778134712 @default.
- W3204752575 hasConcept C31972630 @default.
- W3204752575 hasConcept C41008148 @default.
- W3204752575 hasConceptScore W3204752575C115961682 @default.
- W3204752575 hasConceptScore W3204752575C120665830 @default.
- W3204752575 hasConceptScore W3204752575C121332964 @default.
- W3204752575 hasConceptScore W3204752575C154945302 @default.
- W3204752575 hasConceptScore W3204752575C159985019 @default.
- W3204752575 hasConceptScore W3204752575C179458375 @default.
- W3204752575 hasConceptScore W3204752575C192562407 @default.
- W3204752575 hasConceptScore W3204752575C23690007 @default.
- W3204752575 hasConceptScore W3204752575C2778134712 @default.
- W3204752575 hasConceptScore W3204752575C31972630 @default.
- W3204752575 hasConceptScore W3204752575C41008148 @default.
- W3204752575 hasLocation W32047525751 @default.
- W3204752575 hasOpenAccess W3204752575 @default.
- W3204752575 hasPrimaryLocation W32047525751 @default.
- W3204752575 hasRelatedWork W2471962767 @default.
- W3204752575 hasRelatedWork W2962849139 @default.
- W3204752575 hasRelatedWork W2963627347 @default.
- W3204752575 hasRelatedWork W2963926543 @default.
- W3204752575 hasRelatedWork W2964121744 @default.
- W3204752575 hasRelatedWork W2971278627 @default.
- W3204752575 hasRelatedWork W3034968345 @default.
- W3204752575 hasRelatedWork W3092948912 @default.
- W3204752575 hasRelatedWork W3101267796 @default.
- W3204752575 hasRelatedWork W3103242287 @default.
- W3204752575 hasRelatedWork W3109585842 @default.
- W3204752575 hasRelatedWork W3117476483 @default.
- W3204752575 hasRelatedWork W3130983693 @default.
- W3204752575 hasRelatedWork W3173531806 @default.
- W3204752575 hasRelatedWork W3176179930 @default.
- W3204752575 hasRelatedWork W3176368002 @default.
- W3204752575 hasRelatedWork W3177583232 @default.
- W3204752575 hasRelatedWork W3182714435 @default.
- W3204752575 hasRelatedWork W3202037070 @default.
- W3204752575 hasRelatedWork W3202216861 @default.
- W3204752575 isParatext "false" @default.
- W3204752575 isRetracted "false" @default.
- W3204752575 magId "3204752575" @default.
- W3204752575 workType "article" @default.