Viper dataset

The Viper dataset is a visual perception benchmark to facilitate both low-level and high-level vision tasks, e.g., optical flow and semantic segmentation. It consists of videos from a realistic virtual world (i.e. GTA gameplay), which are collected while driving, riding and walking in diverse ambient conditions (day, sunset, snow, rain, and night). Each frame (resolution: 1920 × 1080) is annotated with pix-level labels, i.e., segmentation label map.