GamutNet: Restoring Wide-Gamut Colors for Camera-Captured Images

Most cameras still encode images in the small-gamut sRGB color space. The reliance on sRGB is disappointing as modern display hardware and image-editing software are capable of using wider-gamut color spaces. Converting a small-gamut image to a wider-gamut is a challenging problem. Many devices and software use colorimetric strategies that map colors from the small gamut to their equivalent colors in the wider gamut. This colorimetric approach avoids visual changes in the image but leaves much of the target wide-gamut space unused. Noncolorimetric approaches stretch or expand the small-gamut colors to enhance image colors while risking color distortions. We take a unique approach to gamut expansion by treating it as a restoration problem. A key insight used in our approach is that cameras internally encode images in a wide-gamut color space (i.e., ProPhoto) before compressing and clipping the colors to sRGB's smaller gamut. Based on this insight, we use a softwarebased camera ISP to generate a dataset of 5,000 image pairs of images encoded in both sRGB and ProPhoto. This dataset enables us to train a neural network to perform wide-gamut color restoration. Our deep-learning strategy achieves significant improvements over existing solutions and produces color-rich images with few to no visual artifacts.

Modified Tseng’s Method with Inertial Viscosity Type for Solving Inclusion Problems and Its Application to Image Restoration Problems

In this paper, we study a monotone inclusion problem in the framework of Hilbert spaces. (1) We introduce a new modified Tseng’s method that combines inertial and viscosity techniques. Our aim is to obtain an algorithm with better performance that can be applied to a broader class of mappings. (2) We prove a strong convergence theorem to approximate a solution to the monotone inclusion problem under some mild conditions. (3) We present a modified version of the proposed iterative scheme for solving convex minimization problems. (4) We present numerical examples that satisfy the image restoration problem and illustrate our proposed algorithm’s computational performance.

Multi-Objective Evolutionary Algorithm for Service Restoration in the Presence of Distributed Generation

Distributed Generators (DGs) have been used to improve quality and reliability of service in Distribution Systems (DSs). They can be used to reduce faults impact on System Average Interruption Duration Index by allowing the minimization of healthy out-ofservice (OFS) loads after the occurrence of permanent faults. IEEE also encourages power supply companies and customers to restore OFS loads by intentional islanding. This paper proposes a modification in recently proposed Multi-Objective Evolutionary Algorithm (MOEA) in subpopulation tables to combine intentional islanding of DGs with network reconfiguration to maximize restoration of OFS loads. The idea is to force intentional islanding whenever OFS heathy areas can be fully supplied by DGs. Simulation results (with a DS presented in the literature) have demonstrated the reliability of the MOEA new version to deal with service restoration problem in the presence of DGs.