US Patent Application 17786841. Systems and Methods for Manipulation of Shadows on Portrait Image Frames simplified abstract
Contents
Systems and Methods for Manipulation of Shadows on Portrait Image Frames
Organization Name
Inventor(s)
David Jacobs of Mountain View CA (US)
Yun-Ta Tsai of Mountain View CA (US)
Jonathan T. Barron of Mountain View CA (US)
Xuaner Zhang of Mountain View CA (US)
Systems and Methods for Manipulation of Shadows on Portrait Image Frames - A simplified explanation of the abstract
This abstract first appeared for US patent application 17786841 titled 'Systems and Methods for Manipulation of Shadows on Portrait Image Frames
Simplified Explanation
- The patent application describes a method for training a machine learning model to be used on a mobile device for capturing and adjusting image frames. - The method involves supplying two image frames of a subject in different lighting environments and determining a mask. - The first and second image frames are then combined using the mask to generate a synthetic image. - A score is assigned to the synthetic image, and a machine learning model is trained based on this score. - The trained model can then be used to adjust captured images based on the synthetic image, improving the quality of the final image.
Original Abstract Submitted
Systems and methods described herein may relate to potential methods of training a machine learning model to be implemented on a mobile computing device configured to capture, adjust, and/or store image frames. An example method includes supplying a first image frame of a subject in a setting lit within a first lighting environment and supplying a second image frame of the subject lit within a second lighting environment. The method further includes determining a mask. Additionally, the method includes combining the first image frame and the second image frame according to the mask to generate a synthetic image and assigning a score to the synthetic image. The method also includes training a machine learning model based on the assigned score to adjust a captured image based on the synthetic image.
