146 citations · 562 across the 32 of their papers we have counts for
7 papers · 1 filter
Protecting Geolocation Privacy of Photo Collections
Jinghan Yang, Ayan Chakrabarti, Yevgeniy Vorobeychik
People increasingly share personal information, including their photos and photo collections, on social media. This information, however, can compromise individual privacy, particu…
Basis Prediction Networks for Effective Burst Denoising with Large Kernels
Zhihao Xia, Federico Perazzi, Michaël Gharbi +2
Bursts of images exhibit significant self-similarity across both time and space. This motivates a representation of the kernels as linear combinations of a small set of basis eleme…
Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices
Weidong Cao, Liu Ke, Ayan Chakrabarti +1
Recent works propose neural network- (NN-) inspired analog-to-digital converters (NNADCs) and demonstrate their great potentials in many emerging applications. These NNADCs often r…
Training Image Estimators without Image Ground-Truth
Zhihao Xia, Ayan Chakrabarti
Deep neural networks have been very successful in image estimation applications such as compressive-sensing and image restoration, as a means to estimate images from partial, blurr…
Generating and Exploiting Probabilistic Monocular Depth Estimates
Zhihao Xia, Patrick Sullivan, Ayan Chakrabarti
Beyond depth estimation from a single image, the monocular cue is useful in a broader range of depth inference applications and settings---such as when one can leverage other avail…
Fast Deep Stereo with 2D Convolutional Processing of Cost Signatures
Kyle Yee, Ayan Chakrabarti
Modern neural network-based algorithms are able to produce highly accurate depth estimates from stereo image pairs, nearly matching the reliability of measurements from more expens…
Backprop with Approximate Activations for Memory-efficient Network Training
Ayan Chakrabarti, Benjamin Moseley
Training convolutional neural network models is memory intensive since back-propagation requires storing activations of all intermediate layers. This presents a practical concern w…