Soft-IntroVAE for Continuous Latent space Image Super-Resolution
This addresses the problem of flexible image scaling for various displays, but it appears incremental as it builds on existing methods like Variational AutoEncoders and local implicit representations.
The paper tackles continuous image super-resolution by proposing Soft-introVAE (SVAE-SR), which uses latent space adversarial training and positional encoding to achieve photo-realistic restoration, showing effectiveness in quantitative and qualitative comparisons and generalization to denoising and real-image tasks.
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.