Cityscapes

doi:doi:10.57702/lbd06rix

Cityscapes

The Cityscapes dataset is a large and famous city street scene semantic segmentation dataset. 19 classes of which 30 classes of this dataset are considered for training and evaluation. Each image has a high resolution 2048 × 1024 pixels. Cityscapes has 5,000 images taken from 50 different cities which are all fine annotated.

BibTex:

@dataset{M_Cordts_and_M_Omran_and_S_Ramos_and_T_Rehfeld_and_M_Enzweiler_and_R_Benenson_and_U_Franke_and_S_Roth_and_B_Schiele_2024,
    abstract = {The Cityscapes dataset is a large and famous city street scene semantic segmentation dataset. 19 classes of which 30 classes of this dataset are considered for training and evaluation. Each image has a high resolution 2048 × 1024 pixels. Cityscapes has 5,000 images taken from 50 different cities which are all fine annotated.},
    author = {M. Cordts and M. Omran and S. Ramos and T. Rehfeld and M. Enzweiler and R. Benenson and U. Franke and S. Roth and B. Schiele},
    doi = {10.57702/lbd06rix},
    institution = {No Organization},
    keyword = {'Camera', 'City Streets', 'Cityscapes', 'Cityscapes dataset', 'Computer Vision', 'Depth Estimation', 'Depth estimation', 'Domain Adaptive Semantic Segmentation', 'Driving Scenes', 'Gaze', 'Image Annotation', 'Image Classification', 'Image Dataset', 'Image Processing', 'Image Segmentation', 'Image classification', 'Image-based object detection', 'Instance Segmentation', 'LIDAR', 'Lane Marking', 'Language', 'Large-Scale Dataset', 'Object Detection', 'Object Referring', 'Object detection', 'RGB Images', 'Real Data', 'Real-world dataset', 'Scene', 'Scene Segmentation', 'Scene Understanding', 'Segmentation', 'Semantic', 'Semantic Segmentation', 'Semantic segmentation', 'Street Scene Understanding', 'Understanding', 'Unsupervised Semantic Segmentation', 'Unsupervised depth estimation', 'Urban', 'Urban Scene', 'Urban Scene Understanding', 'Urban Scenes', 'Urban Street Scene', 'Urban driving scenes', 'Urban scene understanding', 'Video', 'autonomous vehicles', 'car detection', 'city street scenes', 'cityscape', 'cityscapes', 'coarse annotations', 'dataset', 'dense annotations', 'domain adaptation', 'high-resolution images', 'image annotation', 'image classification', 'image composition', 'image dataset', 'image forgery', 'image labeling', 'image segmentation', 'image-to-image translation', 'instance segmentation', 'large scale', 'large-scale dataset', 'multi-class', 'object detection', 'object insertion', 'panoptic segmentation', 'pedestrian recognition', 'pixel-level annotations', 'pixel-wise annotation', 'pixel-wise annotations', 'scene manipulation', 'scene parsing', 'segmentation', 'semantic image segmentation', 'semantic maps', 'semantic segmentation', 'street scene', 'street scene understanding', 'street view', 'style transfer', 'synthetic data', 'transformers', 'unsupervised learning', 'urban scene', 'urban scene segmentation', 'urban scene understanding', 'urban scenes', 'urban street scene', 'urban street view', 'video sequences'},
    month = {nov},
    publisher = {TIB},
    title = {Cityscapes},
    url = {https://service.tib.eu/ldmservice/dataset/cityscapes},
    year = {2024}
}