Neural Holography

Holographic displays promise unprecedented capabilities for direct-view displays as well as virtual and augmented reality (VR/AR) applications. However, one of the biggest challenges for computer-generated holography (CGH) is the fundamental tradeoff between algorithm runtime and achieved image quality, which has prevented high-quality holographic image synthesis at fast speeds. Moreover, the image quality achieved by most holographic displays is low, due to the mismatch between physical light transport of the display and its simulated model. Here, we develop an algorithmic CGH framework that achieves unprecedented image fidelity and real-time framerates. Our framework comprises several parts, including a novel camera-in-the-loop optimization strategy that allows us to either optimize a hologram directly or train an interpretable model of the physical light transport and a neural network architecture that represents the first CGH algorithm capable of generating full-color holographic images at 1080p resolution in real time.

Yifan Peng (Stanford University)
Suyeon Choi (Stanford University)
Nitish Padmanaban (Stanford University)
Jonghyun Kim (Stanford University, NVIDIA)
Gordon Wetzstein (Stanford University)
Publication Date: 
Sunday, August 23, 2020
Uploaded Files: