US Patent Application 18028930. Enhanced Photo Relighting Based on Machine Learning Models simplified abstract
Contents
Enhanced Photo Relighting Based on Machine Learning Models
Organization Name
Inventor(s)
Sean Ryan Francesco Fanello of San Francisco CA (US)
Yun-Ta Tsai of Los Gatos CA (US)
Rohit Kumar Pandey of Mountain View CA (US)
Paul Debevec of Culver City CA (US)
Michael Milne of San Mateo CA (US)
Chloe Legendre of Culver City CA (US)
Jonathan Tilton Barron of Alameda CA (US)
Christoph Rhemann of Marina Del Rey CA (US)
Sofien Bouaziz of Los Gatos CA (US)
Navin Padman Sarma of Palo Alto CA (US)
Enhanced Photo Relighting Based on Machine Learning Models - A simplified explanation of the abstract
This abstract first appeared for US patent application 18028930 titled 'Enhanced Photo Relighting Based on Machine Learning Models
Simplified Explanation
- The patent application is related to applying lighting models to images of objects. - The method involves using a geometry model to determine the distribution of lighting on an object based on its surface geometry. - An environmental light estimation model is then used to determine the direction of synthetic lighting to be applied to the image. - A light energy model is applied based on the surface orientation map and the direction of synthetic lighting to determine the amount of light energy to be applied to each pixel of the image. - The method also includes enhancing a portion of the image based on the determined light energy. - The patent application mentions the use of one or more neural networks to perform these aspects.
Original Abstract Submitted
Apparatus and methods related to applying lighting models to images of objects are provided. An example method includes applying a geometry model to an input image to determine a surface orientation map indicative of a distribution of lighting on an object based on a surface geometry. The method further includes applying an environmental light estimation model to the input image to determine a direction of synthetic lighting to be applied to the input image. The method also includes applying, based on the surface orientation map and the direction of synthetic lighting, a light energy model to determine a quotient image indicative of an amount of light energy to be applied to each pixel of the input image. The method additionally includes enhancing, based on the quotient image, a portion of the input image. One or more neural networks can be trained to perform one or more of the aforementioned aspects.
