Hsinchu, Taiwan

Yi-Ting Bao

This inventor holds 5 USPTO granted patents and 1 published patent application. Top assignee: Realtek Semiconductor Inc.. Active years: 2022-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Yi-Ting Bao. Retrieved from https://idiyas.com/inventor/yi-ting-bao

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

USPTO Granted Patents = 5 

% Patents Active = 60.0

Average Co-Inventor Count = 3.4

ph-index = 1

Forward Citations = 1(Granted Patents)


Company Filing History:


Years Active: 2022-2026

Loading Chart...
5 patents (USPTO):Explore Patents

Title: Innovations of Yi-Ting Bao

Introduction

Yi-Ting Bao is a prominent inventor based in Hsinchu, Taiwan. He has made significant contributions to the field of image processing, particularly through his innovative patents. With a total of three patents to his name, Bao continues to push the boundaries of technology in his area of expertise.

Latest Patents

One of Yi-Ting Bao's latest patents is the "Super resolution image generation circuit." This invention includes an image scale-up circuit, a stable SR processing circuit, a generative adversarial network (GAN) processing circuit, and a configurable basic block pool circuit. The image scale-up circuit processes an input image to generate a scaled-up image. The stable SR processing circuit generates a stable delta value from the feature map of the input image. The GAN processing circuit produces a GAN delta value, while the configurable basic block pool circuit dynamically configures basic blocks based on the depth requirement of the input image. Ultimately, the SR image generation circuit synthesizes an SR image using the scaled-up image, stable delta value, and GAN delta value.

Another notable patent is the "Image enlarging apparatus and method having super resolution enlarging mechanism." This invention outlines a method where an enlarging module of a neural network system receives an input image to generate an enlarged image. The front end convolutional path performs convolution on the input image to produce an output result. Branching convolutional paths generate groups of

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…