CamVid

The dataset used in the paper is a pre-trained ResNet-50 classifier, which is used for image synthesis, unpaired image-to-image translation, and feature similarity estimation.

Data and Resources

Cite this as

G. J. Brostow, J. Shotton, J. Fauqueur, R. Cipolla (2024). Dataset: CamVid. https://doi.org/10.57702/t0wqghr8

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2107.02393
Citation
  • https://doi.org/10.48550/arXiv.2007.05441
  • https://doi.org/10.48550/arXiv.1907.11357
  • https://doi.org/10.1109/TITS.2019.2922252
  • https://doi.org/10.48550/arXiv.2402.02430
  • https://doi.org/10.48550/arXiv.1909.00179
  • https://doi.org/10.48550/arXiv.1811.08201
  • https://doi.org/10.48550/arXiv.2006.02706
  • https://doi.org/10.48550/arXiv.2103.12212
  • https://doi.org/10.48550/arXiv.2002.07317
  • https://doi.org/10.48550/arXiv.1807.06132
Author G. J. Brostow
More Authors
J. Shotton
J. Fauqueur
R. Cipolla
Homepage https://www.robots.ox.ac.uk/~vgg/data/camvid/