Image Enhancement via Bilateral Learning

TL;DR

This paper presents a novel image enhancement system combining convolutional neural networks and bilateral grid techniques, achieving improved results through increased training data, model size, and a variable training rate.

Contribution

It introduces a new CNN-based image enhancement method that effectively integrates bilateral grid, with strategies like data augmentation and variable training rate for better performance.

Findings

Quantitative improvements over existing methods

Qualitative enhancement of image quality

Effective integration of CNN and bilateral grid

Abstract

Nowadays, due to advanced digital imaging technologies and internet accessibility to the public, the number of generated digital images has increased dramatically. Thus, the need for automatic image enhancement techniques is quite apparent. In recent years, deep learning has been used effectively. Here, after introducing some recently developed works on image enhancement, an image enhancement system based on convolutional neural networks is presented. Our goal is to make an effective use of two available approaches, convolutional neural network and bilateral grid. In our approach, we increase the training data and the model dimensions and propose a variable rate during the training process. The enhancement results produced by our proposed method, while incorporating 5 different experts, show both quantitative and qualitative improvements as compared to other available methods.