We propose a real-world animation video super-resolution method VQD-SR, which utilizes a multi-scale VQGAN to decompose the local details from global structures and transfer the degradation priors ...
Abstract: By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback