Images obtained under adverse weather conditions, such as haze or fog, typically/nexhibit low contrast and faded colors, which may severely limit the visibility within the scene. Unveiling/nthe image structure under the haze layer and recovering vivid colors out of a single image/nremains a challenging task, since the degradation is depth-dependent and conventional methods are/nunable to overcome this problem. In this work, we extend a well-known perception-inspired variational/nframework for single image dehazing. Two main improvements are proposed. First, we replace/nthe value used by the framework for the grey-world hypothesis by an estimation of the mean of/nthe clean image. Second, we add a set of new terms to the energy functional for maximizing the/ninter-channel contrast. Experimental results show that the proposed Enhanced Variational Image/nDehazing (EVID) method outperforms other state-of-the-art methods both qualitatively and quantitatively./nIn particular, when the illuminant is uneven, our EVID method is the only one that recovers/nrealistic colors, avoiding the appearance of strong chromatic artifacts.

D. Pardo was partially funded by the Project of the Spanish Ministry of Economy and Competitiveness with reference MTM2013-40824-P, the BCAM “Severo Ochoa” accreditation of excellence SEV-2013-0323, the CYTED 2011 project 712RT0449, and the Basque Government/nConsolidated Research Group Grant IT649-13 on “Mathematical Modeling, Simulation, and Industrial Applications (M2SI)”.