US Patent Application 18304651. STANDARD DYNAMIC RANGE (SDR) TO HIGH DYNAMIC RANGE (HDR)INVERSE TONE MAPPING USING MACHINE LEARNING simplified abstract
STANDARD DYNAMIC RANGE (SDR) TO HIGH DYNAMIC RANGE (HDR)INVERSE TONE MAPPING USING MACHINE LEARNING
Organization Name
Inventor(s)
Chenguang Liu of Tustin CA (US)
Dung Trung Vo of Costa Mesa CA (US)
McClain Craig Nelson of Anaheim CA (US)
Chang Su of Foothill Ranch CA (US)
STANDARD DYNAMIC RANGE (SDR) TO HIGH DYNAMIC RANGE (HDR)INVERSE TONE MAPPING USING MACHINE LEARNING - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 18304651 Titled 'STANDARD DYNAMIC RANGE (SDR) TO HIGH DYNAMIC RANGE (HDR)INVERSE TONE MAPPING USING MACHINE LEARNING'
Simplified Explanation
This abstract describes a method that takes in standard dynamic range (SDR) content and uses statistics information to determine parameters for an inverse tone mapping (ITM) curve. The ITM curve is then used to convert the SDR content into high dynamic range (HDR) content. The resulting HDR content is then displayed on a display device.
Original Abstract Submitted
One embodiment provides a method comprising receiving, as input, standard dynamic range (SDR) content, and obtaining statistics information corresponding to the SDR content. The method further comprises determining, based on the statistics information, one or more parameters for an inverse tone mapping (ITM) curve using a machine learning model. The method further comprises converting the SDR content to high dynamic range (HDR) content using the ITM curve. The resulting HDR content is provided to a display device for presentation.