Viper dataset

doi:doi:10.57702/iywas1al

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.

BibTex:

@dataset{Aayush_Bansal_and_Shugao_Ma_and_Deva_Ramanan_and_Yaser_Sheikh_2024,
    abstract = {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.},
    author = {Aayush Bansal and Shugao Ma and Deva Ramanan and Yaser Sheikh},
    doi = {10.57702/iywas1al},
    institution = {No Organization},
    keyword = {'Multimodal Dataset', 'Unsupervised Learning', 'Video Segmentation', 'Video-to-Video Translation', 'Viper', 'Visual Perception', 'image-to-labels', 'labels-to-image', 'semantic labels', 'video'},
    month = {nov},
    publisher = {TIB},
    title = {Viper dataset},
    url = {https://service.tib.eu/ldmservice/dataset/viper-dataset},
    year = {2024}
}