Single Image Super-Resolution via a Dual Interactive Implicit Neural Network

TL;DR

This paper presents a novel implicit neural network for single image super-resolution at arbitrary scales, effectively decoupling content and positional features to produce high-quality images with a single model.

Contribution

The proposed dual interactive neural network introduces a fully implicit, scale-flexible approach that separates content and positional features for super-resolution.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Supports arbitrary scale factors with a single model

Demonstrates high-quality super-resolution results

Abstract

In this paper, we introduce a novel implicit neural network for the task of single image super-resolution at arbitrary scale factors. To do this, we represent an image as a decoding function that maps locations in the image along with their associated features to their reciprocal pixel attributes. Since the pixel locations are continuous in this representation, our method can refer to any location in an image of varying resolution. To retrieve an image of a particular resolution, we apply a decoding function to a grid of locations each of which refers to the center of a pixel in the output image. In contrast to other techniques, our dual interactive neural network decouples content and positional features. As a result, we obtain a fully implicit representation of the image that solves the super-resolution problem at (real-valued) elective scales using a single model. We demonstrate the efficacy and flexibility of our approach against the state of the art on publicly available benchmark datasets.