Light Field Super resolution: A Bayesian Approach

Tom Bishop


Abstract

We present our prototype light field camera system, and demonstrate its application to reconstructing high-resolution images and depth maps of a scene from a single snapshot.

These types of cameras sample the light field of a scene by trading off spatial resolution with angular resolution. Current methods to process the resulting light field produce images at a resolution that is much lower than that of traditional imaging devices.

However, by explicitly modeling the image formation process and incorporating priors such as Lambertianity and texture statistics, these types of images can be reconstructed at a higher resolution. We formulate a solution under the Bayesian framework to reconstruct both the depth map of the scene, and the super resolved radiance image. We demonstrate the method on both synthetic and real images captured with our light-field camera prototype.


Maintained by Dian Gong