Alejandro Acosta

TL;DR: SRGAN as mentioned in this paper proposes a perceptual loss function which consists of an adversarial loss and a content loss, which pushes the solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images.

TL;DR: SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.

TL;DR: In this article, a spatio-temporal sub-pixel convolution network is proposed to exploit temporal redundancies and improve reconstruction accuracy while maintaining real-time speed, and a novel joint motion compensation and video super-resolution algorithm that is orders of magnitude more efficient than competing methods.

TL;DR: A multi-scale generative adversarial network for frame interpolation (FIGAN) that is jointly supervised at different levels with a perceptual loss function that consists of an adversarial and two content losses to improve the quality of synthesised intermediate video frames.

TL;DR: A novel joint motion compensation and video super-resolution algorithm that is orders of magnitude more efficient than competing methods, relying on a fast multi-resolution spatial transformer module that is end-to-end trainable is proposed.