Super-resolution of Omnidirectional Images Using Adversarial Learning
This work addresses the need for high-resolution content in immersive VR systems, representing an incremental improvement in ODI super-resolution.
The paper tackles super-resolution for omnidirectional images (ODIs) to enhance immersive virtual reality systems, proposing an improved GAN-based model with a fast PatchGAN discriminator and a spherical-content loss function, achieving efficacy as demonstrated on a dataset of 4500 ODIs.
An omnidirectional image (ODI) enables viewers to look in every direction from a fixed point through a head-mounted display providing an immersive experience compared to that of a standard image. Designing immersive virtual reality systems with ODIs is challenging as they require high resolution content. In this paper, we study super-resolution for ODIs and propose an improved generative adversarial network based model which is optimized to handle the artifacts obtained in the spherical observational space. Specifically, we propose to use a fast PatchGAN discriminator, as it needs fewer parameters and improves the super-resolution at a fine scale. We also explore the generative models with adversarial learning by introducing a spherical-content specific loss function, called 360-SS. To train and test the performance of our proposed model we prepare a dataset of 4500 ODIs. Our results demonstrate the efficacy of the proposed method and identify new challenges in ODI super-resolution for future investigations.