Training-Free, Single-Image Super-Resolution Using a Dynamic Convolutional Network

Bhowmik, Aritra and Shit, Suprosanna and Seelamantula, Chandra Sekhar (2018) Training-Free, Single-Image Super-Resolution Using a Dynamic Convolutional Network. In: IEEE SIGNAL PROCESSING LETTERS, 25 (1). pp. 85-89.

PDF IEEE_SIG_PRO_25-1_85_2018.pdf - Published Version Restricted to Registered users only Download (466kB) | Request a copy

Abstract

The typical approach for solving the problem of single-image super-resolution (SR) is to learn a nonlinear mapping between the low-resolution (LR) and high-resolution (HR) representations of images in a training set. Training-based approaches can be tuned to give high accuracy on a given class of images, but they call for retraining if the HR -> LR generative model deviates or if the test images belong to a different class, which limits their applicability. On the other hand, we propose a solution that does not require a training dataset. Our method relies on constructing a dynamic convolutional network (DCN) to learn the relation between the consecutive scales of Gaussian and Laplacian pyramids. The relation is in turn used to predict the detail at a finer scale, thus leading to SR. Comparisons with state-of-the-art techniques on standard datasets show that the proposed DCN approach results in about 0.8 and 0.3 dB gain in peak signal-to-noise ratio for 2x and 3x SR, respectively. The structural similarity index is on par with the competing techniques.

Item Type:	Journal Article
Publication:	IEEE SIGNAL PROCESSING LETTERS
Publisher:	10.1109/LSP.2017.2752806
Additional Information:	Copy right for this article belongs to the IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 445 HOES LANE, PISCATAWAY, NJ 08855-4141 USA
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	13 Jan 2018 07:38
Last Modified:	13 Jan 2018 07:38
URI:	http://eprints.iisc.ac.in/id/eprint/58569

Actions (login required)

View Item