Matches in SemOpenAlex for { <https://semopenalex.org/work/W2966324615> ?p ?o ?g. }
- W2966324615 abstract "High-dynamic-range (HDR) imaging is crucial for many computer graphics and vision applications. Yet, acquiring HDR images with a single shot remains a challenging problem. Whereas modern deep learning approaches are successful at hallucinating plausible HDR content from a single low-dynamic-range (LDR) image, saturated scene details often cannot be faithfully recovered. Inspired by recent deep optical imaging approaches, we interpret this problem as jointly training an optical encoder and electronic decoder where the encoder is parameterized by the point spread function (PSF) of the lens, the bottleneck is the sensor with a limited dynamic range, and the decoder is a convolutional neural network (CNN). The lens surface is then jointly optimized with the CNN in a training phase; we fabricate this optimized optical element and attach it as a hardware add-on to a conventional camera during inference. In extensive simulations and with a physical prototype, we demonstrate that this end-to-end deep optical imaging approach to single-shot HDR imaging outperforms both purely CNN-based approaches and other PSF engineering approaches." @default.
- W2966324615 created "2019-08-13" @default.
- W2966324615 creator A5033862822 @default.
- W2966324615 creator A5053110194 @default.
- W2966324615 creator A5071514078 @default.
- W2966324615 creator A5088204867 @default.
- W2966324615 date "2019-08-01" @default.
- W2966324615 modified "2023-09-27" @default.
- W2966324615 title "Deep Optics for Single-shot High-dynamic-range Imaging" @default.
- W2966324615 cites W1483393136 @default.
- W2966324615 cites W1494666760 @default.
- W2966324615 cites W1505723240 @default.
- W2966324615 cites W1583366798 @default.
- W2966324615 cites W1658472922 @default.
- W2966324615 cites W1901129140 @default.
- W2966324615 cites W1987371344 @default.
- W2966324615 cites W1995813543 @default.
- W2966324615 cites W1998041589 @default.
- W2966324615 cites W1998393535 @default.
- W2966324615 cites W2010316810 @default.
- W2966324615 cites W2014131801 @default.
- W2966324615 cites W2031835363 @default.
- W2966324615 cites W2050262943 @default.
- W2966324615 cites W2054927225 @default.
- W2966324615 cites W2062385952 @default.
- W2966324615 cites W2063069461 @default.
- W2966324615 cites W2064000601 @default.
- W2966324615 cites W2064619906 @default.
- W2966324615 cites W2069281566 @default.
- W2966324615 cites W2071435687 @default.
- W2966324615 cites W2074172223 @default.
- W2966324615 cites W2080701608 @default.
- W2966324615 cites W2081404530 @default.
- W2966324615 cites W2084136084 @default.
- W2966324615 cites W2084591647 @default.
- W2966324615 cites W2098691629 @default.
- W2966324615 cites W2103802376 @default.
- W2966324615 cites W2108637563 @default.
- W2966324615 cites W2109804663 @default.
- W2966324615 cites W2119967924 @default.
- W2966324615 cites W2121729750 @default.
- W2966324615 cites W2130700878 @default.
- W2966324615 cites W2130724993 @default.
- W2966324615 cites W2137313943 @default.
- W2966324615 cites W2141432549 @default.
- W2966324615 cites W2151351002 @default.
- W2966324615 cites W2154571593 @default.
- W2966324615 cites W2155617382 @default.
- W2966324615 cites W2156566307 @default.
- W2966324615 cites W2161008509 @default.
- W2966324615 cites W2304846792 @default.
- W2966324615 cites W2330285287 @default.
- W2966324615 cites W2436863189 @default.
- W2966324615 cites W2474071559 @default.
- W2966324615 cites W2487564216 @default.
- W2966324615 cites W2537300680 @default.
- W2966324615 cites W2552290192 @default.
- W2966324615 cites W2736611505 @default.
- W2966324615 cites W2760005823 @default.
- W2966324615 cites W2769930525 @default.
- W2966324615 cites W2770113520 @default.
- W2966324615 cites W2799224898 @default.
- W2966324615 cites W2809008759 @default.
- W2966324615 cites W2809900749 @default.
- W2966324615 cites W2887566712 @default.
- W2966324615 cites W2894939846 @default.
- W2966324615 cites W2916119524 @default.
- W2966324615 cites W2930326357 @default.
- W2966324615 cites W2949479960 @default.
- W2966324615 cites W2956039874 @default.
- W2966324615 cites W2958407396 @default.
- W2966324615 cites W2963181968 @default.
- W2966324615 cites W2991172647 @default.
- W2966324615 cites W3014223636 @default.
- W2966324615 cites W3106403396 @default.
- W2966324615 cites W2047027620 @default.
- W2966324615 hasPublicationYear "2019" @default.
- W2966324615 type Work @default.
- W2966324615 sameAs 2966324615 @default.
- W2966324615 citedByCount "2" @default.
- W2966324615 countsByYear W29663246152020 @default.
- W2966324615 crossrefType "posted-content" @default.
- W2966324615 hasAuthorship W2966324615A5033862822 @default.
- W2966324615 hasAuthorship W2966324615A5053110194 @default.
- W2966324615 hasAuthorship W2966324615A5071514078 @default.
- W2966324615 hasAuthorship W2966324615A5088204867 @default.
- W2966324615 hasConcept C108583219 @default.
- W2966324615 hasConcept C115961682 @default.
- W2966324615 hasConcept C120665830 @default.
- W2966324615 hasConcept C121332964 @default.
- W2966324615 hasConcept C121684516 @default.
- W2966324615 hasConcept C146044194 @default.
- W2966324615 hasConcept C15336307 @default.
- W2966324615 hasConcept C154945302 @default.
- W2966324615 hasConcept C2780056265 @default.
- W2966324615 hasConcept C2781399445 @default.
- W2966324615 hasConcept C31972630 @default.
- W2966324615 hasConcept C41008148 @default.
- W2966324615 hasConcept C81363708 @default.
- W2966324615 hasConcept C8641274 @default.