CVAug 23, 2017

Fast single image super-resolution based on sigmoid transformation

arXiv:1708.07029v31 citations
Originality Incremental advance
AI Analysis

This work addresses the ill-posed problem of generating high-resolution images from low-resolution ones, with potential applications in various fields, but it appears incremental as it builds on existing regularization techniques.

The paper tackles single image super-resolution by introducing a fast strategy using patch-wise sigmoid transformation as a sharpening regularization term, achieving superior reconstruction performance and efficiency compared to state-of-the-art methods.

Single image super-resolution aims to generate a high-resolution image from a single low-resolution image, which is of great significance in extensive applications. As an ill-posed problem, numerous methods have been proposed to reconstruct the missing image details based on exemplars or priors. In this paper, we propose a fast and simple single image super-resolution strategy utilizing patch-wise sigmoid transformation as an imposed sharpening regularization term in the reconstruction, which realizes amazing reconstruction performance. Extensive experiments compared with other state-of-the-art approaches demonstrate the superior effectiveness and efficiency of the proposed algorithm.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes