You're currently viewing an old version of this dataset. To see the current version, click here.

Vimeo-90K

The proposed StableVSR is built upon a pre-trained Latent Diffusion Model (LDM) for single image super-resolution (SISR). We use Stable Diffusion ×4 Upscaler (SD×4Upscaler)2. It follows the LDM framework [31], which performs the iterative refinement process into a latent space and uses the VAE decoder D [11] to decode latents into RGB images.

Data and Resources

Cite this as

Claudio Rota, Marco Buzzelli, Joost van de Weijer (2024). Dataset: Vimeo-90K. https://doi.org/10.57702/yl0zbzrs

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.2311.15908
Citation
  • https://doi.org/10.48550/arXiv.2302.05071
  • https://doi.org/10.48550/arXiv.2406.16544
  • https://doi.org/10.1007/s11263-018-01144-2
  • https://doi.org/10.48550/arXiv.2106.07190
Author Claudio Rota
More Authors
Marco Buzzelli
Joost van de Weijer
Homepage https://vimeo.com/90k