Vimeo-90K

doi:doi:10.57702/yl0zbzrs

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.

BibTex:

@dataset{Claudio_Rota_and_Marco_Buzzelli_and_Joost_van_de_Weijer_2024,
    abstract = {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.},
    author = {Claudio Rota and Marco Buzzelli and Joost van de Weijer},
    doi = {10.57702/yl0zbzrs},
    institution = {No Organization},
    keyword = {'Compression', 'Diffusion Models', 'Hierarchical B-frame', 'High-quality frames', 'Latent Diffusion Models', 'Low-Level Video Processing', 'Task-Oriented Video Enhancement', 'Video', 'Video Enhancement', 'Video Super-Resolution', 'Vimeo-90K', 'image compression', 'neural networks'},
    month = {dec},
    publisher = {TIB},
    title = {Vimeo-90K},
    url = {https://service.tib.eu/ldmservice/dataset/vimeo-90k},
    year = {2024}
}