FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3154388980> ?p ?o ?g. }

• W3154388980 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.
• W3154388980 created "2021-04-26" @default.
• W3154388980 creator A5037547726 @default.
• W3154388980 creator A5055053078 @default.
• W3154388980 creator A5067998833 @default.
• W3154388980 creator A5085020955 @default.
• W3154388980 date "2021-04-13" @default.
• W3154388980 modified "2023-09-27" @default.
• W3154388980 title "BARF: Bundle-Adjusting Neural Radiance Fields" @default.
• W3154388980 cites W1488812736 @default.
• W3154388980 cites W1489405158 @default.
• W3154388980 cites W1906648922 @default.
• W3154388980 cites W1971719398 @default.
• W3154388980 cites W1986528120 @default.
• W3154388980 cites W2033819227 @default.
• W3154388980 cites W2063366997 @default.
• W3154388980 cites W2080629029 @default.
• W3154388980 cites W2098362450 @default.
• W3154388980 cites W2108134361 @default.
• W3154388980 cites W2108598243 @default.
• W3154388980 cites W2118877769 @default.
• W3154388980 cites W2119781527 @default.
• W3154388980 cites W2126521141 @default.
• W3154388980 cites W2129201358 @default.
• W3154388980 cites W2140950877 @default.
• W3154388980 cites W2152671441 @default.
• W3154388980 cites W2156598602 @default.
• W3154388980 cites W2163446794 @default.
• W3154388980 cites W2474281075 @default.
• W3154388980 cites W2609883120 @default.
• W3154388980 cites W2770128544 @default.
• W3154388980 cites W2808492412 @default.
• W3154388980 cites W2883907768 @default.
• W3154388980 cites W2943445277 @default.
• W3154388980 cites W2949336566 @default.
• W3154388980 cites W2949657144 @default.
• W3154388980 cites W2949825757 @default.
• W3154388980 cites W2962785568 @default.
• W3154388980 cites W2963403868 @default.
• W3154388980 cites W2963557767 @default.
• W3154388980 cites W2963562098 @default.
• W3154388980 cites W2963583471 @default.
• W3154388980 cites W2963604511 @default.
• W3154388980 cites W2963654727 @default.
• W3154388980 cites W2964121744 @default.
• W3154388980 cites W2964189516 @default.
• W3154388980 cites W2964288609 @default.
• W3154388980 cites W2971278627 @default.
• W3154388980 cites W3016007010 @default.
• W3154388980 cites W3034528136 @default.
• W3154388980 cites W3034801905 @default.
• W3154388980 cites W3035524985 @default.
• W3154388980 cites W3043075211 @default.
• W3154388980 cites W3092948912 @default.
• W3154388980 cites W3101267796 @default.
• W3154388980 cites W3103242287 @default.
• W3154388980 cites W3107486934 @default.
• W3154388980 cites W3108311884 @default.
• W3154388980 cites W3109244019 @default.
• W3154388980 cites W3109420014 @default.
• W3154388980 cites W3109476562 @default.
• W3154388980 cites W3109585842 @default.
• W3154388980 cites W3112108866 @default.
• W3154388980 cites W3113005628 @default.
• W3154388980 cites W3113347918 @default.
• W3154388980 cites W3129710562 @default.
• W3154388980 cites W3130983693 @default.
• W3154388980 cites W3167914619 @default.
• W3154388980 cites W3176368002 @default.
• W3154388980 cites W3184952021 @default.
• W3154388980 cites W3199643754 @default.
• W3154388980 cites W3206768813 @default.
• W3154388980 cites W612478963 @default.
• W3154388980 doi "https://doi.org/10.48550/arxiv.2104.06405" @default.
• W3154388980 hasPublicationYear "2021" @default.
• W3154388980 type Work @default.
• W3154388980 sameAs 3154388980 @default.
• W3154388980 citedByCount "1" @default.
• W3154388980 countsByYear W31543889802021 @default.
• W3154388980 crossrefType "posted-content" @default.
• W3154388980 hasAuthorship W3154388980A5037547726 @default.
• W3154388980 hasAuthorship W3154388980A5055053078 @default.
• W3154388980 hasAuthorship W3154388980A5067998833 @default.
• W3154388980 hasAuthorship W3154388980A5085020955 @default.
• W3154388980 hasBestOaLocation W31543889801 @default.
• W3154388980 hasConcept C115961682 @default.
• W3154388980 hasConcept C154945302 @default.
• W3154388980 hasConcept C159985019 @default.
• W3154388980 hasConcept C179458375 @default.
• W3154388980 hasConcept C192562407 @default.
• W3154388980 hasConcept C205649164 @default.
• W3154388980 hasConcept C23690007 @default.
• W3154388980 hasConcept C2778134712 @default.
• W3154388980 hasConcept C31972630 @default.
• W3154388980 hasConcept C41008148 @default.
• W3154388980 hasConcept C62649853 @default.
• W3154388980 hasConceptScore W3154388980C115961682 @default.
• W3154388980 hasConceptScore W3154388980C154945302 @default.
• W3154388980 hasConceptScore W3154388980C159985019 @default.
• W3154388980 hasConceptScore W3154388980C179458375 @default.

• next