180-degree Outpainting from a Single Image
This addresses the limitation of standard cameras' small field-of-view for immersive visual applications, though it appears incremental as it builds on existing image generation techniques.
The paper tackles the problem of generating 180-degree panoramic images from narrow-view images to enhance immersive visual experiences, achieving feasibility and promising results through a deep learning approach.
Presenting context images to a viewer's peripheral vision is one of the most effective techniques to enhance immersive visual experiences. However, most images only present a narrow view, since the field-of-view (FoV) of standard cameras is small. To overcome this limitation, we propose a deep learning approach that learns to predict a 180° panoramic image from a narrow-view image. Specifically, we design a foveated framework that applies different strategies on near-periphery and mid-periphery regions. Two networks are trained separately, and then are employed jointly to sequentially perform narrow-to-90° generation and 90°-to-180° generation. The generated outputs are then fused with their aligned inputs to produce expanded equirectangular images for viewing. Our experimental results show that single-view-to-panoramic image generation using deep learning is both feasible and promising.