Self-Supervised Shadow Removal
This addresses the challenge of shadow removal in computer vision, which is important for applications like photo editing and autonomous systems, by eliminating the need for paired data, though it is incremental as it builds on existing self-supervised learning methods.
The paper tackles the problem of single image shadow removal without requiring paired shadowed and shadow-free training images, achieving state-of-the-art performance on ISTD and USR datasets.
Shadow removal is an important computer vision task aiming at the detection and successful removal of the shadow produced by an occluded light source and a photo-realistic restoration of the image contents. Decades of re-search produced a multitude of hand-crafted restoration techniques and, more recently, learned solutions from shad-owed and shadow-free training image pairs. In this work,we propose an unsupervised single image shadow removal solution via self-supervised learning by using a conditioned mask. In contrast to existing literature, we do not require paired shadowed and shadow-free images, instead we rely on self-supervision and jointly learn deep models to remove and add shadows to images. We validate our approach on the recently introduced ISTD and USR datasets. We largely improve quantitatively and qualitatively over the compared methods and set a new state-of-the-art performance in single image shadow removal.