HARP: Autoregressive Latent Video Prediction With High-Fidelity Image Generator

in image super-resolution reconstruction based on generative adversarial networks (GANs), the discrimination of high-resolution (HR) images enriches texture details. However, solely discriminating HR images limits the reconstruction quality, while discriminating other resolution features can improve the texture structures of the reconstructed HR images. Therefore, this paper proposes a SAR image super-resolution reconstruction algorithm based on full-resolution discrimination (FRD). in the suggested architecture, the full-resolution discriminator network is used to extract the high, medium, and low-resolution features, which are then fused into a full-resolution feature. Finally, the full-resolution feature difference between the authentic and fake images is input to the generator, which reduces the inaccuracy of single-resolution feature discrimination. Experimental results on synthetic aperture radar (SAR) images demonstrate that the proposed FRD algorithm performs better than the state-of-the-art super-resolution algorithms in reconstructing the texture structures of the HR SAR images.