Controllable Image Enhancement

TL;DR

This paper introduces a semi-automatic image enhancement method that uses a compact encoder-decoder model to generate high-quality, styled images by controlling a few parameters, achieving state-of-the-art results.

Contribution

The proposed approach disentangles retouching skills from images and encodes them into latent codes to control image enhancement with only 19 parameters, improving efficiency and quality.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Uses only 19 parameters for image signal processing.

Requires multiple inferences but maintains high quality.

Abstract

Editing flat-looking images into stunning photographs requires skill and time. Automated image enhancement algorithms have attracted increased interest by generating high-quality images without user interaction. However, the quality assessment of a photograph is subjective. Even in tone and color adjustments, a single photograph of auto-enhancement is challenging to fit user preferences which are subtle and even changeable. To address this problem, we present a semiautomatic image enhancement algorithm that can generate high-quality images with multiple styles by controlling a few parameters. We first disentangle photo retouching skills from high-quality images and build an efficient enhancement system for each skill. Specifically, an encoder-decoder framework encodes the retouching skills into latent codes and decodes them into the parameters of image signal processing (ISP) functions. The ISP functions are computationally efficient and consist of only 19 parameters. Despite our approach requiring multiple inferences to obtain the desired result, experimental results present that the proposed method achieves state-of-the-art performances on the benchmark dataset for image quality and model efficiency.