TPCNet: Triple physical constraints for Low-light Image Enhancement
This work addresses low-light image enhancement for computer vision applications, offering an incremental improvement by refining physical constraints in existing Retinex-based models.
The paper tackled the problem of low-light image enhancement by introducing a new physical constraint theory based on Kubelka-Munk theory to account for specular reflection, resulting in improved performance metrics and visual quality without adding parameters, outperforming state-of-the-art methods on 10 datasets.
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.