379 citations · 411 across the 4 of their papers we have counts for
5 papers
CNN-Based Projected Gradient Descent for Consistent Image Reconstruction
Harshit Gupta, Kyong Hwan Jin, Ha Q. Nguyen +2
We present a new method for image reconstruction which replaces the projector in a projected gradient descent (PGD) with a convolutional neural network (CNN). CNNs trained as high-…
Approximation of Non-Decaying Signals From Shift-Invariant Subspaces
Ha Q. Nguyen, Michael Unser
In our recent work, the sampling and reconstruction of non-decaying signals, modeled as members of weighted- spaces, were shown to be stable with an appropriate choice of the…
Learning Convex Regularizers for Optimal Bayesian Denoising
Ha Q. Nguyen, Emrah Bostan, Michael Unser
We propose a data-driven algorithm for the maximum a posteriori (MAP) estimation of stochastic processes from noisy observations. The primary statistical properties of the sought s…
Frame Permutation Quantization
Ha Q. Nguyen, Vivek K Goyal, Lav R. Varshney
Frame permutation quantization (FPQ) is a new vector quantization technique using finite frames. In FPQ, a vector is encoded using a permutation source code to quantize its frame e…
Concentric Permutation Source Codes
Ha Q. Nguyen, Lav R. Varshney, Vivek K Goyal
Permutation codes are a class of structured vector quantizers with a computationally-simple encoding procedure based on sorting the scalar components. Using a codebook comprising s…