Edge-oriented Implicit Neural Representation with Channel Tuning

TL;DR

This paper introduces EoREN, a novel implicit neural representation model that enhances image reconstruction by explicitly focusing on edge clarity through gradient adjustment and channel tuning modules.

Contribution

The paper proposes a new Edge-oriented Representation Network with gradient and channel tuning modules to improve edge reconstruction in implicit neural representations.

Findings

EoREN effectively reconstructs images with clearer edges.

The model achieves superior results in complex signal reconstruction.

It maintains true image colors while enhancing edge details.

Abstract

Implicit neural representation, which expresses an image as a continuous function rather than a discrete grid form, is widely used for image processing. Despite its outperforming results, there are still remaining limitations on restoring clear shapes of a given signal such as the edges of an image. In this paper, we propose Gradient Magnitude Adjustment algorithm which calculates the gradient of an image for training the implicit representation. In addition, we propose Edge-oriented Representation Network (EoREN) that can reconstruct the image with clear edges by fitting gradient information (Edge-oriented module). Furthermore, we add Channel-tuning module to adjust the distribution of given signals so that it solves a chronic problem of fitting gradients. By separating backpropagation paths of the two modules, EoREN can learn true color of the image without hindering the role for gradients. We qualitatively show that our model can reconstruct complex signals and demonstrate general reconstruction ability of our model with quantitative results.