ViViD++ : Vision for Visibility Dataset

In this letter, we present a dataset capturing diverse visual data formats that target varying luminance conditions. While RGB cameras provide nourishing and intuitive information, changes in lighting conditions potentially result catastrophic failure for robotic applications based on vision sensors. Approaches overcoming illumination problems have included developing more robust algorithms or other types of sensors, such as thermal event cameras. Despite the alternative sensors’ potential, there still are few datasets with Thus, provided recorded from by handheld mounted car, repeatedly same space but different We aim to acquire visible information co-aligned Our sensor system collects independently light intensity measuring amount infrared dissipation, depth structured reflection, instantaneous temporal luminance. these measurements along inertial sensors ground-truth SLAM under poor illumination.