XCycles Backprojection Acoustic Super-Resolution

TL;DR

This paper introduces XCycles Backprojection, a novel acoustic image super-resolution model that leverages iterative correction, along with a new dataset, to significantly improve resolution and reduce sampling errors in acoustic imaging.

Contribution

It proposes a backprojection-based super-resolution model for acoustic images and introduces the AMIVU dataset, advancing acoustic image resolution techniques beyond existing methods.

Findings

XCBP outperforms classical interpolation and recent feedforward models.

The approach reduces sub-sampling errors during data acquisition.

The dataset enables effective training and evaluation of acoustic SR methods.

Abstract

The computer vision community has paid much attention to the development of visible image super-resolution (SR) using deep neural networks (DNNs) and has achieved impressive results. The advancement of non-visible light sensors, such as acoustic imaging sensors, has attracted much attention, as they allow people to visualize the intensity of sound waves beyond the visible spectrum. However, because of the limitations imposed on acquiring acoustic data, new methods for improving the resolution of the acoustic images are necessary. At this time, there is no acoustic imaging dataset designed for the SR problem. This work proposed a novel backprojection model architecture for the acoustic image super-resolution problem, together with Acoustic Map Imaging VUB-ULB Dataset (AMIVU). The dataset provides large simulated and real captured images at different resolutions. The proposed XCycles BackProjection model (XCBP), in contrast to the feedforward model approach, fully uses the iterative correction procedure in each cycle to reconstruct the residual error correction for the encoded features in both low- and high-resolution space. The proposed approach was evaluated on the dataset and showed high outperformance compared to the classical interpolation operators and to the recent feedforward state-of-the-art models. It also contributed to a drastically reduced sub-sampling error produced during the data acquisition.