18386147. NEURAL NETWORK-BASED ANTI-ALIASING FOR HAIR RENDERING (Tencent America LLC)
NEURAL NETWORK-BASED ANTI-ALIASING FOR HAIR RENDERING
Organization Name
Inventor(s)
Rundong Wu of Mountain View CA US
NEURAL NETWORK-BASED ANTI-ALIASING FOR HAIR RENDERING
This abstract first appeared for US patent application 18386147 titled 'NEURAL NETWORK-BASED ANTI-ALIASING FOR HAIR RENDERING
Original Abstract Submitted
A method of hair rendering includes acquiring a color input image and an opacity input image from a hair rendering system, the color input image and the opacity input image having a first sample resolution. The method further includes providing the color input image and the opacity input image as input to a trained neural network configured to generate an intermediate color output image and an intermediate opacity output image by performing an anti-aliasing function on the color input image and the opacity input image. The method further includes performing hair rendering based on the intermediate color output image and the intermediate opacity output image to generate a final rendered hair image.