CURL: Neural Curve Layers for Global Image Enhancement

TL;DR

CURL introduces neural curve layers inspired by Photoshop tools, enabling global image enhancement across multiple colour spaces, trained end-to-end, and achieving state-of-the-art results in photo enhancement tasks.

Contribution

The paper proposes a novel neural curve layer approach trained jointly in HSV, CIELab, and RGB spaces, improving global image enhancement performance.

Findings

Achieves state-of-the-art image quality metrics.

Effective in both photo enhancement and image signal processing.

Outperforms recent deep learning approaches on multiple datasets.

Abstract

We present a novel approach to adjust global image properties such as colour, saturation, and luminance using human-interpretable image enhancement curves, inspired by the Photoshop curves tool. Our method, dubbed neural CURve Layers (CURL), is designed as a multi-colour space neural retouching block trained jointly in three different colour spaces (HSV, CIELab, RGB) guided by a novel multi-colour space loss. The curves are fully differentiable and are trained end-to-end for different computer vision problems including photo enhancement (RGB-to-RGB) and as part of the image signal processing pipeline for image formation (RAW-to-RGB). To demonstrate the effectiveness of CURL we combine this global image transformation block with a pixel-level (local) image multi-scale encoder-decoder backbone network. In an extensive experimental evaluation we show that CURL produces state-of-the-art image quality versus recently proposed deep learning approaches in both objective and perceptual metrics, setting new state-of-the-art performance on multiple public datasets. Our code is publicly available at: https://github.com/sjmoran/CURL.