LUT-GCE: Lookup Table Global Curve Estimation for Fast Low-light Image Enhancement

TL;DR

LUT-GCE introduces a fast, global curve-based method for low-light image enhancement using a lightweight neural network and lookup tables, outperforming existing methods in speed and quality.

Contribution

The paper proposes a novel cubic curve formulation and a lightweight global curve estimation network with a lookup table for rapid low-light image enhancement.

Findings

Outperforms state-of-the-art in inference speed, especially on high-resolution images.

Achieves better contrast and detail recovery through a histogram smoothness loss.

Demonstrates effectiveness with both quantitative metrics and qualitative results.

Abstract

We present an effective and efficient approach for low-light image enhancement, named Lookup Table Global Curve Estimation (LUT-GCE). In contrast to existing curve-based methods with pixel-wise adjustment, we propose to estimate a global curve for the entire image that allows corrections for both under- and over-exposure. Specifically, we develop a novel cubic curve formulation for light enhancement, which enables an image-adaptive and pixel-independent curve for the range adjustment of an image. We then propose a global curve estimation network (GCENet), a very light network with only 25.4k parameters. To further speed up the inference speed, a lookup table method is employed for fast retrieval. In addition, a novel histogram smoothness loss is designed to enable zero-shot learning, which is able to improve the contrast of the image and recover clearer details. Quantitative and qualitative results demonstrate the effectiveness of the proposed approach. Furthermore, our approach outperforms the state of the art in terms of inference speed, especially on high-definition images (e.g., 1080p and 4k).