Semi-LLIE: Semi-supervised Contrastive Learning with Mamba-based Low-light Image Enhancement

TL;DR

Semi-LLIE introduces a semi-supervised framework for low-light image enhancement that combines semantic-aware contrastive loss, a Mamba-based backbone, and vision-language perceptive loss to improve color fidelity, detail, and realism.

Contribution

It proposes a novel semi-supervised low-light enhancement method integrating a semantic-aware contrastive loss and a Mamba-based backbone to better restore details and natural colors.

Findings

Outperforms existing methods in quantitative metrics

Generates images with richer textures and natural colors

Effectively restores details in dark areas

Abstract

Despite the impressive advancements made in recent low-light image enhancement techniques, the scarcity of paired data has emerged as a significant obstacle to further advancements. This work proposes a mean-teacher-based semi-supervised low-light enhancement (Semi-LLIE) framework that integrates the unpaired data into model training. The mean-teacher technique is a prominent semi-supervised learning method, successfully adopted for addressing high-level and low-level vision tasks. However, two primary issues hinder the naive mean-teacher method from attaining optimal performance in low-light image enhancement. Firstly, pixel-wise consistency loss is insufficient for transferring realistic illumination distribution from the teacher to the student model, which results in color cast in the enhanced images. Secondly, cutting-edge image enhancement approaches fail to effectively cooperate with the mean-teacher framework to restore detailed information in dark areas due to their tendency to overlook modeling structured information within local regions. To mitigate the above issues, we first introduce a semantic-aware contrastive loss to faithfully transfer the illumination distribution, contributing to enhancing images with natural colors. Then, we design a Mamba-based low-light image enhancement backbone to effectively enhance Mamba's local region pixel relationship representation ability with a multi-scale feature learning scheme, facilitating the generation of images with rich textural details. Further, we propose novel perceptive loss based on the large-scale vision-language Recognize Anything Model (RAM) to help generate enhanced images with richer textual details. The experimental results indicate that our Semi-LLIE surpasses existing methods in both quantitative and qualitative metrics.