5 datasets found

The GTA dataset consists of 24966 synthetic images synthetically generated from a video game consisting of outdoor scenes with rich variety of variations in lighting and traffic...

The NTIRE2018-Dehazing challenge dataset contains indoor and outdoor hazy images.

The RESIDE dataset contains both synthesized and real-world hazy/clean image pairs of indoor and outdoor scenes.

Feature matching is a fundamental problem for many computer vision tasks, such as object recognition, structure from motion, and simultaneous localization and mapping.

The dataset used for training and validation of the proposed approach to combine semantic segmentation and dense outlier detection.