activity
20172022
most citedFourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

1.2k citations · 1.5k across the 13 of their papers we have counts for

collaborators
Showing 2019Show all

5 papers · 1 filter

eess.IV2019

Video from Stills: Lensless Imaging with Rolling Shutter

Nick Antipa, Patrick Oare, Emrah Bostan +2

Because image sensor chips have a finite bandwidth with which to read out pixels, recording video typically requires a trade-off between frame rate and pixel count. Compressed sens…

cs.CV2019★ 4 cited

Synthetic Defocus and Look-Ahead Autofocus for Casual Videography

Xuaner Zhang, Kevin Matzen, Vivien Nguyen +3

In cinema, large camera lenses create beautiful shallow depth of field (DOF), but make focusing difficult and expensive. Accurate cinema focus usually relies on a script and a pers…

cs.CV2019

Zoom To Learn, Learn To Zoom

Xuaner Cecilia Zhang, Qifeng Chen, Ren Ng +1

This paper shows that when applying machine learning to digital zoom for photography, it is beneficial to use real, RAW sensor data for training. Existing learning-based super-reso…

cs.CV2019★ 10 cited

Pushing the Boundaries of View Extrapolation with Multiplane Images

Pratul P. Srinivasan, Richard Tucker, Jonathan T. Barron +3

We explore the problem of view synthesis from a narrow baseline pair of images, and focus on generating high-quality view extrapolations with plausible disocclusions. Our method bu…

cs.CV2019★ 28 cited

StegaStamp: Invisible Hyperlinks in Physical Photographs

Matthew Tancik, Ben Mildenhall, Ren Ng

Printed and digitally displayed photos have the ability to hide imperceptible digital data that can be accessed through internet-connected imaging systems. Another way to think abo…