Neural 3D Holography

Holographic near-eye displays promise unprecedented capabilities for virtual and augmented reality (VR/AR) systems. The image quality achieved by current holographic displays, however, is limited by the wave propagation models used to simulate the physical optics. We propose a neural network–parameterized plane-to-multiplane wave propagation model that closes the gap between physics and simulation. Our model is automatically trained using camera feedback and it outperforms related techniques in 2D plane-to-plane settings by a large margin. Moreover, it is the first network-parameterized model to naturally extend to 3D settings, enabling high-quality 3D computer-generated holography using a novel phase regularization strategy of the complex-valued wave field. The efficacy of our approach is demonstrated through extensive experimental evaluation with both VR and optical see-through AR display prototypes.

https://youtu.be/EsxGnUd8Efs

Authors

Suyeon Choi (Stanford University)
Manu Gopakumar (Stanford University)
Yifan Peng (Stanford University)
Gordon Wetzstein (Stanford University)

Publication Date

Uploaded Files

paper17.03 MB