Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137123492> ?p ?o ?g. }
- W3137123492 abstract "Across a wide range of applications, from autonomous vehicles to medical imaging, multi-spectral images provide an opportunity to extract additional information not present in color images. One of the most important steps in making this information readily available is the accurate estimation of dense correspondences between different spectra. Due to the nature of cross-spectral images, most correspondence solving techniques for the visual domain are simply not applicable. Furthermore, most cross-spectral techniques utilize spectra-specific characteristics to perform the alignment. In this work, we aim to address the dense correspondence estimation problem in a way that generalizes to more than one spectrum. We do this by introducing a novel cycle-consistency metric that allows us to self-supervise. This, combined with our spectra-agnostic loss functions, allows us to train the same network across multiple spectra. We demonstrate our approach on the challenging task of dense RGB-FIR correspondence estimation. We also show the performance of our unmodified network on the cases of RGB-NIR and RGB-RGB, where we achieve higher accuracy than similar self-supervised approaches. Our work shows that cross-spectral correspondence estimation can be solved in a common framework that learns to generalize alignment across spectra." @default.
- W3137123492 created "2021-03-29" @default.
- W3137123492 creator A5033644268 @default.
- W3137123492 creator A5044490167 @default.
- W3137123492 creator A5054989551 @default.
- W3137123492 creator A5073833451 @default.
- W3137123492 date "2021-03-19" @default.
- W3137123492 modified "2023-09-23" @default.
- W3137123492 title "There and Back Again: Self-supervised Multispectral Correspondence Estimation" @default.
- W3137123492 cites W1530110590 @default.
- W3137123492 cites W1874027545 @default.
- W3137123492 cites W1910108985 @default.
- W3137123492 cites W1936798282 @default.
- W3137123492 cites W2005626749 @default.
- W3137123492 cites W2012893378 @default.
- W3137123492 cites W2033687086 @default.
- W3137123492 cites W2039094769 @default.
- W3137123492 cites W2049981393 @default.
- W3137123492 cites W2090518410 @default.
- W3137123492 cites W2104853049 @default.
- W3137123492 cites W2105466713 @default.
- W3137123492 cites W2115579991 @default.
- W3137123492 cites W2116367120 @default.
- W3137123492 cites W2118877769 @default.
- W3137123492 cites W2120339103 @default.
- W3137123492 cites W2120339771 @default.
- W3137123492 cites W2124351162 @default.
- W3137123492 cites W2126277110 @default.
- W3137123492 cites W2151103935 @default.
- W3137123492 cites W2209124607 @default.
- W3137123492 cites W2331128040 @default.
- W3137123492 cites W2340546455 @default.
- W3137123492 cites W2340671224 @default.
- W3137123492 cites W2468674378 @default.
- W3137123492 cites W2512785428 @default.
- W3137123492 cites W2520707372 @default.
- W3137123492 cites W2527415613 @default.
- W3137123492 cites W2560474170 @default.
- W3137123492 cites W2741160171 @default.
- W3137123492 cites W2770424797 @default.
- W3137123492 cites W2789934631 @default.
- W3137123492 cites W2798881637 @default.
- W3137123492 cites W2800106563 @default.
- W3137123492 cites W2803832867 @default.
- W3137123492 cites W2803875274 @default.
- W3137123492 cites W2806446538 @default.
- W3137123492 cites W2890222793 @default.
- W3137123492 cites W2890949887 @default.
- W3137123492 cites W2894983388 @default.
- W3137123492 cites W2897770165 @default.
- W3137123492 cites W2913269858 @default.
- W3137123492 cites W2922074212 @default.
- W3137123492 cites W2946406946 @default.
- W3137123492 cites W2949023359 @default.
- W3137123492 cites W2949676527 @default.
- W3137123492 cites W2950111065 @default.
- W3137123492 cites W2963097011 @default.
- W3137123492 cites W2963782415 @default.
- W3137123492 cites W2963891416 @default.
- W3137123492 cites W2964156315 @default.
- W3137123492 cites W2969790287 @default.
- W3137123492 cites W3003686015 @default.
- W3137123492 cites W764651262 @default.
- W3137123492 hasPublicationYear "2021" @default.
- W3137123492 type Work @default.
- W3137123492 sameAs 3137123492 @default.
- W3137123492 citedByCount "0" @default.
- W3137123492 crossrefType "posted-content" @default.
- W3137123492 hasAuthorship W3137123492A5033644268 @default.
- W3137123492 hasAuthorship W3137123492A5044490167 @default.
- W3137123492 hasAuthorship W3137123492A5054989551 @default.
- W3137123492 hasAuthorship W3137123492A5073833451 @default.
- W3137123492 hasConcept C153180895 @default.
- W3137123492 hasConcept C154945302 @default.
- W3137123492 hasConcept C159985019 @default.
- W3137123492 hasConcept C162324750 @default.
- W3137123492 hasConcept C173163844 @default.
- W3137123492 hasConcept C176217482 @default.
- W3137123492 hasConcept C187736073 @default.
- W3137123492 hasConcept C192562407 @default.
- W3137123492 hasConcept C204323151 @default.
- W3137123492 hasConcept C21547014 @default.
- W3137123492 hasConcept C2776436953 @default.
- W3137123492 hasConcept C2780451532 @default.
- W3137123492 hasConcept C31972630 @default.
- W3137123492 hasConcept C41008148 @default.
- W3137123492 hasConcept C82990744 @default.
- W3137123492 hasConceptScore W3137123492C153180895 @default.
- W3137123492 hasConceptScore W3137123492C154945302 @default.
- W3137123492 hasConceptScore W3137123492C159985019 @default.
- W3137123492 hasConceptScore W3137123492C162324750 @default.
- W3137123492 hasConceptScore W3137123492C173163844 @default.
- W3137123492 hasConceptScore W3137123492C176217482 @default.
- W3137123492 hasConceptScore W3137123492C187736073 @default.
- W3137123492 hasConceptScore W3137123492C192562407 @default.
- W3137123492 hasConceptScore W3137123492C204323151 @default.
- W3137123492 hasConceptScore W3137123492C21547014 @default.
- W3137123492 hasConceptScore W3137123492C2776436953 @default.
- W3137123492 hasConceptScore W3137123492C2780451532 @default.
- W3137123492 hasConceptScore W3137123492C31972630 @default.