GT-Mean Loss: A Simple Yet Effective Solution for Brightness Mismatch in Low-Light Image Enhancement

2025-07-27

AI Summary

A prevalent yet long-overlooked issue in supervised low-light image enhancement (LLIE) is brightness mismatch between enhanced outputs and ground-truth images, leading to training bias. This paper is the first to systematically identify and analyze this phenomenon. We propose GT-mean loss—a principled extension of standard L1/L2 losses—by probabilistically modeling the distribution of image mean intensities and enforcing explicit ground-truth mean constraints. The loss is plug-and-play: it integrates seamlessly into existing supervised frameworks without introducing additional parameters or measurable computational overhead, and remains compatible with mainstream LLIE methods. Extensive experiments across multiple benchmarks and base models demonstrate that GT-mean consistently improves PSNR and SSIM while effectively mitigating brightness mismatch. Our approach provides a simple, parameter-free, and broadly applicable brightness calibration solution for supervised LLIE.

Technology Category

Machine Learning: Calibration & Uncertainty QuantificationComputer Vision: Adversarial Attacks & RobustnessNatural Language Processing: Language Grounding & Multi-modal NLP

Application Category

Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Low-light image enhancement (LLIE) aims to improve the visual quality of images captured under poor lighting conditions. In supervised LLIE research, there exists a significant yet often overlooked inconsistency between the overall brightness of an enhanced image and its ground truth counterpart, referred to as brightness mismatch in this study. Brightness mismatch negatively impact supervised LLIE models by misleading model training. However, this issue is largely neglected in current research. In this context, we propose the GT-mean loss, a simple yet effective loss function directly modeling the mean values of images from a probabilistic perspective. The GT-mean loss is flexible, as it extends existing supervised LLIE loss functions into the GT-mean form with minimal additional computational costs. Extensive experiments demonstrate that the incorporation of the GT-mean loss results in consistent performance improvements across various methods and datasets.

Problem

• Addresses brightness mismatch in low-light image enhancement
• Proposes GT-mean loss to improve model training accuracy
• Enhances performance across multiple methods and datasets

Innovation

• Proposes GT-mean loss for brightness mismatch
• Models image mean values probabilistically
• Extends existing LLIE loss functions flexibly