LoopExpose: An Unsupervised Framework for Arbitrary-Length Exposure Correction

TL;DR

LoopExpose is an unsupervised framework that uses a nested loop optimization and a feedback mechanism to improve arbitrary-length exposure correction without requiring large labeled datasets.

Contribution

It introduces a novel pseudo label-based unsupervised method with a nested loop strategy and luminance ranking loss for improved exposure correction.

Findings

Outperforms existing unsupervised methods on benchmark datasets.

Effectively corrects exposure in images with challenging lighting.

Demonstrates robustness across different image sequences.

Abstract

Exposure correction is essential for enhancing image quality under challenging lighting conditions. While supervised learning has achieved significant progress in this area, it relies heavily on large-scale labeled datasets, which are difficult to obtain in practical scenarios. To address this limitation, we propose a pseudo label-based unsupervised method called LoopExpose for arbitrary-length exposure correction. A nested loop optimization strategy is proposed to address the exposure correction problem, where the correction model and pseudo-supervised information are jointly optimized in a two-level framework. Specifically, the upper-level trains a correction model using pseudo-labels generated through multi-exposure fusion at the lower level. A feedback mechanism is introduced where corrected images are fed back into the fusion process to refine the pseudo-labels, creating a self-reinforcing learning loop. Considering the dominant role of luminance calibration in exposure correction, a Luminance Ranking Loss is introduced to leverage the relative luminance ordering across the input sequence as a self-supervised constraint. Extensive experiments on different benchmark datasets demonstrate that LoopExpose achieves superior exposure correction and fusion performance, outperforming existing state-of-the-art unsupervised methods. Code is available at https://github.com/FALALAS/LoopExpose.