Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

TLDR

Zero‑DCE does not require paired or unpaired reference images and may improve face detection in low‑light scenes. The authors propose Zero‑Reference Deep Curve Estimation to enhance low‑light images by learning image‑specific curves with a deep network. A lightweight DCE‑Net estimates pixel‑wise high‑order curves, trained with non‑reference losses that enforce pixel‑value range, monotonicity, and differentiability. The method is efficient, generalizes across lighting conditions, and outperforms state‑of‑the‑art techniques on multiple benchmarks while also benefiting face detection in darkness.

Abstract

The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network. Our method trains a lightweight deep network, DCE-Net, to estimate pixel-wise and high-order curves for dynamic range adjustment of a given image. The curve estimation is specially designed, considering pixel value range, monotonicity, and differentiability. Zero-DCE is appealing in its relaxed assumption on reference images, i.e., it does not require any paired or unpaired data during training. This is achieved through a set of carefully formulated non-reference loss functions, which implicitly measure the enhancement quality and drive the learning of the network. Our method is efficient as image enhancement can be achieved by an intuitive and simple nonlinear curve mapping. Despite its simplicity, we show that it generalizes well to diverse lighting conditions. Extensive experiments on various benchmarks demonstrate the advantages of our method over state-of-the-art methods qualitatively and quantitatively. Furthermore, the potential benefits of our Zero-DCE to face detection in the dark are discussed.