A new technique by a group of computer scientists at Virginia Tech, National Tsing Hua University, and Facebook can turn regular photos into 3D-style pictures using a technique that extrapolates the backgrounds of still photos.
From the abstract:
We propose a method for converting a single RGB-D input image into a 3D photo, i.e., a multi-layer representation for novel view synthesis that contains hallucinated color and depth structures in regions occluded in the original view. We use a Layered Depth Image with explicit pixel connectivity as underlying representation, and present a learning-based inpainting model that iteratively synthesizes new local color-and-depth content into the occluded region in a spatial context-aware manner. The resulting 3D photos can be efficiently rendered with motion parallax using standard graphics engines. We validate the effectiveness of our method on a wide range of challenging everyday scenes and show fewer artifacts when compared with the state-of-the-arts.
The system basically looks at a photo and finds the items in the foreground. It then assesses what might appear behind a figure in the foreground, allowing for a 3D-style effect that can look similar to the Ken Burns effect or something like the newspaper images in Harry Potter.
Ultimately this is a gimmick but given the power of modern phones it could be coming to a photo sharing app near you.
