“…While some approaches consider multiple images as input (from multiple viewpoints [CBLD11, LBP * 12, Laf12, LBD13, HWU * 14, Duc15, XLL * 16], varying illumination [Wei01,MLKS04,Yu16], or different focal distances [SSN16]), images with depth information [BM13, CK13, JCTL14, HGW15], multi-spectral images [SW09], videos [YGL * 14, BST * 14, KGB14, SYC * 14, MZRT16], lightfields [GEZ * 16, AG16] or even videos with depth [LZT * 12], this document focuses on the use of a single RGB image as input, and emphasizes image editing applications. This is motivated by the wide availability of this kind of data and the need for illumination-aware image editing tools.…”