Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer for Exposure Correction

TL;DR

This paper introduces a hierarchical transformer model that effectively corrects exposure issues in photographs by capturing both local and global features, outperforming existing methods in visual quality and detail restoration.

Contribution

The paper proposes a novel Macro-Micro-Hierarchical transformer with a contrast constraint for improved exposure correction and low-light image enhancement.

Findings

Outperforms state-of-the-art exposure correction methods quantitatively.

Effectively restores color and details in over-/under-exposed regions.

Enhances low-light face recognition and semantic segmentation.

Abstract

Photographs taken with less-than-ideal exposure settings often display poor visual quality. Since the correction procedures vary significantly, it is difficult for a single neural network to handle all exposure problems. Moreover, the inherent limitations of convolutions, hinder the models ability to restore faithful color or details on extremely over-/under- exposed regions. To overcome these limitations, we propose a Macro-Micro-Hierarchical transformer, which consists of a macro attention to capture long-range dependencies, a micro attention to extract local features, and a hierarchical structure for coarse-to-fine correction. In specific, the complementary macro-micro attention designs enhance locality while allowing global interactions. The hierarchical structure enables the network to correct exposure errors of different scales layer by layer. Furthermore, we propose a contrast constraint and couple it seamlessly in the loss function, where the corrected image is pulled towards the positive sample and pushed away from the dynamically generated negative samples. Thus the remaining color distortion and loss of detail can be removed. We also extend our method as an image enhancer for low-light face recognition and low-light semantic segmentation. Experiments demonstrate that our approach obtains more attractive results than state-of-the-art methods quantitatively and qualitatively.