P‐4.13: Flexible multi‐view synthesis from a single image

This paper proposes a multi‐view autostereoscopic content synthesis technique for glasses‐free 3D display devices. This technology uses deep learning methods to construct 3D implicit representations to ensure geometric consistency between viewpoints. At inferencing time, our method takes a single RGB image as input and generates a 3D implicit representation of the input view frustum. When rendering new viewpoints, the size of the 3D content's parallax, the screen‐in/out ratio, and the number of viewpoints can be adjusted by setting the external parameters of the virtual camera. Thus, it can adapt to glasses‐free 3D display devices with different optical designs.