The vector hybrid Wiener filter: Application to super-resolution

Abstract

We address the problem of recovering a continuous-time (space) signal from several blurred and noisy sampled versions of it, a scenario commonly encountered in super-resolution (SR) and arrayprocessing. We show that discretization, a key step in many SR algorithms, inevitably leads to inaccurate modeling. Instead, we treat the problem entirely in the continuous domain by modeling the signal as a continuous-time random process and deriving its linear minimum mean-squared error estimate given the samples. We also provide an efficient implementation scheme, valid for 1D applications. Simulation results on real-world data demonstrate the advantage of our approach with respect to SR techniques that rely on discretization.

A Hybrid Transformation and Filtering Approach for Speech Enhancement with Time Domain Pitch Synchronous Overlap-add

“…PESQ is defined in ITU-T recommendation P.862 and is also studied in Muralishankar et al (2004) is an objective measurement tool that forecast the outcome of subjective listening tests. It uses a sensory model to evaluate the original, unprocessed signals with the improved signals.…”

Increasing satellite imagery resolution by fusion of data from multiple spatially shifted CCDs: a spectral-based approach

“…Papers (Feuer 2004;Feuer and Goodwin 2005) have got important addition to Cheung (1993) and consider the case of recurrent sampling (1). The problem seems to have been solved and the following papers (e.g., Eldar and Michaeli 2009) use more complicated models of the original signal S instead of restoration of the signal with finite spectrum. …”