research
∙
07/10/2023
Substance or Style: What Does Your Image Embedding Know?
Probes are small networks that predict properties of underlying data fro...
share
research
∙
01/30/2023
Benchmarking Robustness to Adversarial Image Obfuscations
Automated content filtering and moderation is an important tool that all...
research
∙
07/31/2022
Adaptive Edge Offloading for Image Classification Under Rate Limit
This paper considers a setting where embedded devices are used to acquir...
research
∙
10/21/2021
PROVES: Establishing Image Provenance using Semantic Signatures
Modern AI tools, such as generative adversarial networks, have transform...
research
∙
03/26/2021
Understanding Robustness of Transformers for Image Classification
Deep Convolutional Neural Networks (CNNs) have long been the architectur...
research
∙
12/09/2020
Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments
We introduce a neural network-based method to denoise pairs of images ta...
research
∙
10/26/2020
Real-Time Edge Classification: Optimal Offloading under Token Bucket Constraints
To deploy machine learning-based algorithms for real-time applications w...
research
∙
10/17/2020
Finding Physical Adversarial Examples for Autonomous Driving with Fast and Differentiable Image Compositing
There is considerable evidence that deep neural networks are vulnerable ...
research
∙
03/21/2020
A MEMS-based Foveating LIDAR to enable Real-time Adaptive Depth Sensing
Most active depth sensors sample their visual field using a fixed patter...
research
∙
12/09/2019
Basis Prediction Networks for Effective Burst Denoising with Large Kernels
Bursts of images exhibit significant self-similarity across both time an...
research
∙
12/04/2019
Protecting Geolocation Privacy of Photo Collections
People increasingly share personal information, including their photos a...
research
∙
11/28/2019
Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices
Recent works propose neural network- (NN-) inspired analog-to-digital co...
research
∙
06/13/2019
Training Image Estimators without Image Ground-Truth
Deep neural networks have been very successful in image estimation appli...
research
∙
06/13/2019
Generating and Exploiting Probabilistic Monocular Depth Estimates
Despite the remarkable success of modern monocular depth estimation meth...
research
∙
03/08/2019
Fast Deep Stereo with 2D Convolutional Processing of Cost Signatures
Modern neural network-based algorithms are able to produce highly accura...
research
∙
01/23/2019
Backprop with Approximate Activations for Memory-efficient Network Training
Larger and deeper neural network architectures deliver improved accuracy...
research
∙
11/29/2018
Learning to Separate Multiple Illuminants in a Single Image
We present a method to separate a single image captured under two illumi...
research
∙
06/13/2018
Identifying Recurring Patterns with Deep Neural Networks for Natural Image Denoising
While there is a vast diversity in the patterns and textures that occur ...
research
∙
02/14/2018
Learning Privacy Preserving Encodings through Adversarial Training
We present a framework to learn privacy-preserving encodings of images (...
research
∙
01/04/2018
Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning
The physical design of a robot and the policy that controls its motion a...
research
∙
05/22/2017
Stabilizing GAN Training with Multiple Random Projections
Training generative adversarial networks is unstable in high-dimensions ...
research
∙
11/17/2016
Examining the Impact of Blur on Recognition by Convolutional Networks
State-of-the-art algorithms for many semantic visual tasks are based on ...
research
∙
09/14/2016
Single-image RGB Photometric Stereo With Spatially-varying Albedo
We present a single-shot system to recover surface geometry of objects w...
research
∙
05/23/2016
Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions
A single color image can contain many cues informative towards different...
research
∙
05/23/2016
Learning Sensor Multiplexing Design through Back-propagation
Recent progress on many imaging and vision tasks has been driven by the ...
research
∙
03/15/2016
A Neural Approach to Blind Motion Deblurring
We present a new method for blind motion deblurring that uses a neural n...
research
∙
06/06/2015
Color Constancy by Learning to Predict Chromaticity from Luminance
Color constancy is the recovery of true surface color from observed colo...
research
∙
11/18/2014
Low-level Vision by Consensus in a Spatial Hierarchy of Regions
We introduce a multi-scale framework for low-level vision, where the goa...
research
∙
11/27/2013
Modeling Radiometric Uncertainty for Vision with Tone-mapped Color Images
To produce images that are suitable for display, tone-mapping is widely ...
research
∙
10/10/2013
From Shading to Local Shape
We develop a framework for extracting a concise representation of the sh...
research
∙
04/13/2012