DeepFocus is a generic, end-to-end convolutional neural network designed to efficiently solve the full range of computational tasks for accommodation-supporting HMDs. This network is demonstrated to accurately synthesize defocus blur, focal stacks, multilayer decompositions, and multiview imagery using only commonly available RGB-D images, enabling real-time, near-correct depictions of retinal blur with a broad set of accommodation-supporting HMDs.

Related Content

DeepFocus: Learned Image Synthesis for Computational Displays

Lei Xiao, Anton S. Kaplanyan, Alexander Fix, Matthew Chapman, Douglas Lanman

December 4, 2018

DeepFocus: Learned Image Synthesis for Computational Display

Lei Xiao, Anton Kaplanyan, Alexander Fix, Matt Chapman, Douglas Lanman

July 6, 2018