Soft-IntroVAE for Continuous Latent space Image Super-Resolution

TL;DR

This paper introduces Soft-IntroVAE for continuous image super-resolution, leveraging latent space adversarial training and positional encoding to enhance photo-realistic image quality and generalization.

Contribution

It presents a novel Soft-IntroVAE model with latent adversarial training and positional encoding for improved continuous image super-resolution.

Findings

Achieves high-quality photo-realistic super-resolution

Demonstrates effective generalization to denoising and real-image SR

Outperforms existing methods in quantitative and qualitative metrics

Abstract

Continuous image super-resolution (SR) recently receives a lot of attention from researchers, for its practical and flexible image scaling for various displays. Local implicit image representation is one of the methods that can map the coordinates and 2D features for latent space interpolation. Inspired by Variational AutoEncoder, we propose a Soft-introVAE for continuous latent space image super-resolution (SVAE-SR). A novel latent space adversarial training is achieved for photo-realistic image restoration. To further improve the quality, a positional encoding scheme is used to extend the original pixel coordinates by aggregating frequency information over the pixel areas. We show the effectiveness of the proposed SVAE-SR through quantitative and qualitative comparisons, and further, illustrate its generalization in denoising and real-image super-resolution.