1. Presenter: Suyeon Choi (a PhD student at Standford Computational Imaging lab (Prof. Gordon Wetzstein))
2. Presentation Title: Neural Holography for Next-generation Virtual and Augmented Reality Displays
3. Time: 2023. 2. 20 (Mon.) 17:00 pm - 18:00 pm (KST)
4. Location: KI building (E4), Lecture Room Red (B501)(Lecture Room)
ID: 865 3752 1091 / Password: 534hL6
Holographic displays promise unprecedented capabilities for direct-view displays as well as virtual and augmented reality applications, including per-pixel depth, efficient light utilization, and vision correction. However, despite these capabilities, these displays always have been relegated to the status of a perpetually future technology, due to several major challenges such as large benchtop form factors, and the fundamental trade-off between algorithm runtime and achieved image quality. In this talk, I will present co-design approaches of optics and algorithms in holographic near-eye displays that address these challenges. First, I will discuss a compact display system architecture with an eyeglasses-like form factor for virtual reality that can deliver full-color 3D holographic images using a 2.5mm thick optical stack. Next, I will introduce 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 a parameterized model of the optical wave propagation and a neural network architecture that represents the first CGH algorithm capable of generating full-color high-quality holographic images at full-HD resolution in real-time. By incorporating AI advancements into conventional optics and photonics, we can open up new possibilities and enable high-fidelity imaging and display solutions.