360?ø Single Image Super Resolution Via Distortion-Aware Network And Distorted Perspective Images

Effective 360?ø imaging requires a very high resolution because the field of view is extraordinarily high. Single-image super-resolution (SISR) applied to 360?ø imaging has the potential to solve the resolution/quality problem in this modality. In this paper, we exploit existing perspective SISR networks to address this problem by (1) introducing a distortion map as an additional input with the 360?ø-distortion-aware loss function, and (2) augmenting the training 360?ø images by distorting the perspective images. We also present a new 360?ø image dataset from YouTube for training. Our extensive experiments show that how each component contributes to the better transfer from the perspective domain to the 360?ø domain and merging all the ideas leads to the best performance in quantitative and qualitative ways for the 360?ø SISR task.