[ECCV 2022] Local Color Distributions Prior for Image Enhancement

Haoyuan Wang1, Ke Xu1, and Rynson W.H. Lau1
1City University of Hong Kong
Fig.1 in our paper.
Input MSEC (CVPR2021) ZeroDCE (CVPR2020)
RUAS (CVPR2021) Ours (ECCV2022) GT


Existing image enhancement methods are typically designed to address either the over- or under-exposure problem in the input image. When the illumination of the input image contains both over- and under-exposure problems, these existing methods may not work well. We observe from the image statistics that the local color distributions (LCDs) of an image suffering from both problems tend to vary across different regions of the image, depending on the local illuminations. Based on this observation, we propose in this paper to exploit these LCDs as a prior for locating and enhancing the two types of regions (i.e., over-/under-exposed regions). First, we leverage the LCDs to represent these regions, and propose a novel local color distribution embedded (LCDE) module to formulate LCDs in multi-scales to model the correlations across different regions. Second, we propose a dual-illumination learning mechanism to enhance the two types of regions. Third, we construct a new dataset to facilitate the learning process, by following the camera image signal processing (ISP) pipeline to render standard RGB images with both under-/over-exposures from raw data. Extensive experiments demonstrate that the proposed method outperforms existing state-of-the-art methods quantitatively and qualitatively. We will release our codes and dataset.


Some results in our paper are shown below (Zoom in for better view). Our model reconstructs the details in the over-exposed regions as well as the under-exposed regions. See our paper for more comparison experiment results.

Our Method (See paper for more details)