Mediatek Corporation

Tsinghua University

Yu-Cheng Tseng

Pei-Kuei Tsung

Chih-Wen Goo

Kuo-Chiang Lo

Chih-Wei Chen

Yao-Sheng Wang

Tung-Chien Chen

Cheng Lung Jen

Ming-En Shih

Yu-Sheng Lin

Wei-Chung Wang

Chi-Hung Huang

Po-Chi Sung

Cheng-Lung Jen

Kuo-Chen Huang

Chia-Da Lee

Ping-Yuan Tsai

Chun Hsien Wu

Hsin-Min Peng

Tsu Jui Hsu

Yu-Lin Hou

Chih-wei Chen

Yu Chieh Lan

Hsiao-Chien Chiu

An image processing circuit performs super-resolution (SR) operations. The image processing circuit includes memory to store multiple parameter sets of multiple artificial intelligence (AI) models. The image processing circuit further includes an image guidance module, a parameter decision module, and an SR engine. The image guidance module operates to detect a representative feature in an image sequence including a current frame and past frames within a time window. The parameter decision module operates to adjust parameters of one or more AI models based on a measurement of the representative feature. The SR engine operates to process the current frame using the one or more AI models with the adjusted parameters to thereby generate a high-resolution image for display.

Image-guided adjustment to super-resolution operations

A video processing circuit includes an input buffer, an online adaptation circuit, and an artificial intelligence (AI) super-resolution (SR) circuit. The input buffer receives input low-resolution (LR) frames and high-resolution (HR) frames from a video source over a network. The online adaptation circuit forms training pairs, and calculates an update to representative features that characterize the input LR frames using the training pairs. Each training pair formed by one of the input LR frames and one of the HR frames. The AI SR circuit receives the input LR frames from the input buffer and the representative features from the online adaptation circuit. Concurrently with calculating the update to the representative features, the AI SR circuit generates SR frames for display from the input LR frames based on the representative features. Each SR frame has a higher resolution than a corresponding one of the input LR frames.

Online AI super resolution engine and operations

A video processing system includes an input port and a video processing circuit. The input port obtains device information of a display panel. The video processing circuit obtains an input frame and the device information, configures an image enhancement operation according to the device information, generates an output frame by performing the image enhancement operation upon the input frame, and transmits the output frame to the display panel for video playback.

Video processing system for performing artificial intelligence assisted picture quality enhancement and associated video processing method

An apparatus for quantifying residual stress of a birefringent material comprises a light source generating light; a vertical polarizer converting a beam of light into a beam with vertical polarization; a standard material being mounted in front of the vertical polarizer; a horizontal polarizer converting a beam of light into a beam with horizontal polarization; an applied force unit applying different forces to the standard material; a spectrometer being mounted in front of the horizontal polarizer and recording intensity of light passing through the horizontal polarizer and transmittance of the standard material and a processing module being connected to the spectrometer, deriving a stress formula from the applied forces and transmittances of the standard material and obtaining a stress distribution of the birefringent material. A method for quantifying residual stress of a birefringent material is also disclosed.

Apparatus and method for quantifying residual stress of a birefringent material

Growing community of inventors

Hsinchu, Taiwan

Yu-Cheng Tseng