ICCV 2023 - Robust Monocular Depth Estimation under Challenging Conditions

In this episode we discuss Robust Monocular Depth Estimation under Challenging Conditions by Stefano Gasperini, Nils Morbitzer, HyunJun Jung, Nassir Navab, Federico Tombari. The paper addresses the limitations of existing monocular depth estimation methods in challenging lighting and weather conditions. The authors propose md4all, a simple and reliable solution that can handle diverse conditions without modification at inference time. The approach involves generating complex training samples, training the model using self- or full-supervision, and computing standard losses on the original images. Extensive experiments on public datasets demonstrate the effectiveness of the approach, surpassing previous works in both standard and challenging conditions.