Li-Wen Wang

Title: Innovations of Li-Wen Wang in Image Enhancement Technology.

Introduction

Li-Wen Wang is a notable inventor based in Hong Kong, CN. He has made significant contributions to the field of image processing, particularly in enhancing low-light images through innovative neural network technology. His work is recognized for its potential applications in various imaging systems.

Latest Patents

Li-Wen Wang holds a patent for a neural network designed for raw low-light image enhancement. This technology utilizes a neural network that receives mono-color pixels in a Bayer pattern from an image sensor. It interpolates these pixels to generate full-color RGB pixels while improving the image's brightness for better detail. The patent describes a Back-Projection (BP) layer added to each contracting layer in a U-net convolution neural network, which increases feature depth as pixels are downsampled. Additionally, a BP channel shrink layer is incorporated into each expansion layer to upsample and enhance pixel resolution. The convolution layers in the BP layer are responsible for lightening and darkening images to generate an error that is then adjusted and added to a weighted lightened input. The neural network is designed to learn the optimal weightings to correct for noise and error during the lightening process in these BP layers. Noise reduction is further achieved by repeating a convolution and leaky Rectified Linear Unit (lrelu) in series for the first convolution in the BP layer that performs lightening.

Career Highlights

Li-Wen Wang is affiliated with the Hong Kong Applied Science and Technology Research Institute, where he continues to develop and refine his innovative technologies. His work has garnered attention for its practical applications in improving image quality in low-light conditions.

Collaborations

Li-Wen Wang collaborates with esteemed colleagues, including Xingbo Guan and Wan-Chi Siu, who contribute to the advancement of research in image processing technologies.

Conclusion

Li-Wen Wang's contributions to neural network technology for image enhancement demonstrate his innovative spirit and commitment to advancing the field of image processing. His work not only addresses current challenges in low-light imaging but also paves the way for future developments in this area.