TPCNet: Triple physical constraints for Low-light Image Enhancement

TL;DR

This paper introduces TPCNet, a novel low-light image enhancement method based on triple physical constraints derived from Kubelka-Munk theory, improving image quality by modeling reflection, illumination, and detection more accurately.

Contribution

It reformulates physical constraints in the feature space using Kubelka-Munk theory, effectively incorporating specular reflection into low-light image enhancement.

Findings

Outperforms state-of-the-art methods on 10 datasets

Improves both quantitative metrics and visual quality

Does not introduce additional parameters

Abstract

Low-light image enhancement is an essential computer vision task to improve image contrast and to decrease the effects of color bias and noise. Many existing interpretable deep-learning algorithms exploit the Retinex theory as the basis of model design. However, previous Retinex-based algorithms, that consider reflected objects as ideal Lambertian ignore specular reflection in the modeling process and construct the physical constraints in image space, limiting generalization of the model. To address this issue, we preserve the specular reflection coefficient and reformulate the original physical constraints in the imaging process based on the Kubelka-Munk theory, thereby constructing constraint relationship between illumination, reflection, and detection, the so-called triple physical constraints (TPCs)theory. Based on this theory, the physical constraints are constructed in the feature space of the model to obtain the TPC network (TPCNet). Comprehensive quantitative and qualitative benchmark and ablation experiments confirm that these constraints effectively improve the performance metrics and visual quality without introducing new parameters, and demonstrate that our TPCNet outperforms other state-of-the-art methods on 10 datasets.