Image-guided adjustment to super-resolution operations

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, a...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Lin, Yu-Sheng, Shih, Ming-En, Tsai, Ping-Yuan, Tsung, Pei-Kuei, Tseng, Yu-Cheng, Chen, Tung-Chien, Goo, Chih-Wen, Wu, Chun Hsien, Wang, Yao-Sheng, Hsu, Tsu Jui, Lo, Kuo-Chiang, Huang, Kuo-Chen, Chen, Chih-Wei, Peng, Hsin-Min, Jen, Cheng Lung
Format:	Patent
Sprache:	eng
Schlagworte:	ADVERTISING ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICESUSING STATIC MEANS TO PRESENT VARIABLE INFORMATION BASIC ELECTRIC ELEMENTS CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING CRYPTOGRAPHY DISPLAY EDUCATION ELECTRIC COMMUNICATION TECHNIQUE ELECTRIC DIGITAL DATA PROCESSING ELECTRIC SOLID STATE DEVICES NOT OTHERWISE PROVIDED FOR ELECTRICITY IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS PICTORIAL COMMUNICATION, e.g. TELEVISION SEALS SEMICONDUCTOR DEVICES
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	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.