Conference Research Projects

Cleaning up toxic waste: Removing nefarious contributions to recommendation systems

Recommendation systems are becoming increasingly important, as evidenced by the popularity of the Netflix prize and the sophistication of various online shopping systems. With this increase in interest, a new problem of nefarious or false rankings that compromise a recommendation system’s integrity has surfaced. We consider such purposefully erroneous rankings to be a form of […]

Journal Research Projects

Blind Image Deconvolution Using Deep Generative Priors

This article proposes a novel approach to regularize the ill-posed and non-linear blind image deconvolution (blind deblurring) using deep generative networks as priors. We employ two separate pretrained generative networks — given lower-dimensional Gaussian vectors as input, one of the generative models samples from the distribution of sharp images, while the other from that of […]

Conference Research Projects

Invertible generative models for inverse problems: mitigating representation error and dataset bias

Trained generative models have shown remark-able performance as priors for inverse problems in imaging – for example, Generative Adversarial Network priors permit recovery of test images from 5-10x fewer measurements than sparsity priors. Unfortunately, these models may be unable to represent any particular image because of architectural choices, mode collapse, and bias in the training […]

Journal Research Projects

Compressive Sampling of Ensembles
of Correlated Signals

The recently developed theory of Compressive sensing (CS) has shown that sparse signals can be reconstructed from a much smaller number of measurements than their bandwidth suggests. In this paper we present a sampling scheme to acquire ensembles of correlated signals at a sub-Nyquist rate. The sampling architecture uses simple analog building blocks including analog […]

Journal Research Projects

Blind Deconvolution Using Modulated Inputs

This paper considers the blind deconvolution of multiple modulated signals/filters, and an arbitrary filter/signal. Multiple inputs are modulated (pointwise multiplied) with random sign sequences , respectively, and the resultant inputs are convolved against an arbitrary input to yield the measurements , where and denote pointwise multiplication, and circular convolution. Given , we want to recover […]

Journal Research Projects

Compressed Sensing based Robust Phase Retrieval
via Deep Generative Priors

Algorithmic phase retrieval offers an alternative means to recover the phase of optical images without requiring sophisticated measurement setups such as holography. This paper proposes a framework to regularize the highly ill-posed and nonlinear phase retrieval problem through deep generative priors by simply using gradient descent algorithm. We experimentally show effectiveness of the proposed approach […]

  • 1
  • 2
wpChatIcon