Xiaoyun Yuan

Title: Innovations of Xiaoyun Yuan in Light Field Video Processing

Introduction

Xiaoyun Yuan is an accomplished inventor based in Beijing, China. He has made significant contributions to the field of light field video processing, holding a total of 3 patents. His work focuses on developing methods and systems that enhance video processing capabilities without the need for traditional camera systems.

Latest Patents

One of his latest patents is titled "Method and system for camera-free light field video processing with all-optical neural network." This invention discloses a method that includes mapping light field video using a digital micro-mirror device (DMD) and an optical fiber coupler. The process transforms a two-dimensional spatial optical signal into a one-dimensional input optical signal. It also realizes a multiply-accumulate computing model within an all-optical recurrent neural network structure, allowing for efficient processing of the input signal. The system outputs an electronic signal via a photodetector or relays the processed signal through optical fibers, achieving high computing speed and energy efficiency.

Another notable patent is the "Method and apparatus for intelligent light field 3D perception with optoelectronic computing." This method involves capturing and identifying binocular images of a scene within a specific depth range using binocular cameras. It maps depth values to disparity values, creating a disparity range for the scene. The invention includes training a diffraction neural network model and performing forward propagation inference on new input data to output depth classification results for each pixel in the binocular images.

Career Highlights

Xiaoyun Yuan is affiliated with Tsinghua University, where he continues to advance research in optoelectronic computing and light field technologies. His innovative approaches have positioned him as a leading figure in the field.

Collaborations

He collaborates with notable colleagues, including Lu Fang and Tiankuang Zhou, who contribute to his research endeavors.

Conclusion

Xiaoyun Yuan's work in light field video processing represents a significant advancement in the field, showcasing the potential of camera-free systems and all-optical neural networks. His contributions are paving the way for future innovations in video technology.