We introduce the problem of localized glass-reflection removal (LGRR), which targets the removal of highlights caused by light reflections on glass surfaces. Our approach uses an end-to-end convolutional neural network trained on MS-COCO image crops with synthetic reflections generated from real light source images. We propose a cost function that includes image difference terms and show that it improves reflection removal and inpainting compared to standard \(L_1\) and \(L_2\) losses. Experimental results demonstrate that our method effectively reduces localized reflections.