Exploiting Spatial Sparsity For Event Cameras With Visual Transformers

We study unsupervised Retinex decomposition for low light image enhancement. Being an underdetermined problem with infinite solutions, well-suited priors are required to reduce the solution space. in this paper, we analyze the characteristics of low-light images and their illumination component and identify a trivial solution not taken into consideration by the previous unsupervised state-of-the-art methods. The challenge comes from the fact that the trivial solution cannot be suppressed from the feasible set, as it corresponds to the true solution, when the low-light image contains a light source. To address this issue, we propose a new regularization term which lets the model explore as much plausible solutions as before. To demonstrate the efficiency of the proposed prior, we conduct our experiments using deep image priors in a framework similar to the recent work RetinexDIP and an in-depth ablation study. Finally, we observe no more halo artefacts in the restored image. For all-but-one metrics, our approach gives results as good as the supervised state-of-the-art indicating the potential of a generative framework for low-light image enhancement.