N
Neel Joshi
Researcher at Wyss Institute for Biologically Inspired Engineering
Publications - 173
Citations - 11153
Neel Joshi is an academic researcher from Wyss Institute for Biologically Inspired Engineering. The author has contributed to research in topics: Image restoration & Image sensor. The author has an hindex of 51, co-authored 161 publications receiving 9394 citations. Previous affiliations of Neel Joshi include Stanford University & Harvey Mudd College.
Papers
More filters
Journal ArticleDOI
High performance imaging using large camera arrays
Bennett Wilburn,Neel Joshi,Vaibhav Vaish,Eino-Ville Talvala,Emilio Antúnez,Adam Barth,Andrew Adams,Mark Horowitz,Marc Levoy +8 more
TL;DR: A unique array of 100 custom video cameras that are built are described, and their experiences using this array in a range of imaging applications are summarized.
Proceedings ArticleDOI
PSF estimation using sharp edge prediction
TL;DR: An algorithm that estimates non-parametric, spatially-varying blur functions at subpixel resolution from a single image by predicting a ldquosharprdquo version of a blurry input image and uses the two images to solve for a PSF.
Book ChapterDOI
Single image deblurring using motion density functions
TL;DR: A novel single image deblurring method to estimate spatially non-uniform blur that results from camera shake that out-performs current approaches which make the assumption of spatially invariant blur.
Proceedings ArticleDOI
Using plane + parallax for calibrating dense camera arrays
TL;DR: A simple procedure to calibrate camera arrays used to capture light fields using a plane + parallax framework is described and it is shown how to estimate camera positions up to an affine ambiguity, and how to reproject light field images onto a family of planes using only knowledge of planarParallax for one point in the scene.
Journal ArticleDOI
Image deblurring using inertial measurement sensors
TL;DR: This work uses a combination of inexpensive gyroscopes and accelerometers in an energy optimization framework to estimate a blur function from the camera's acceleration and angular velocity during an Exposure to solve for the camera motion at a high sampling rate during an exposure and infer the latent image using a joint optimization.