18949447. High Resolution Inpainting with a Machine-learned Augmentation Model and Texture Transfer (GOOGLE LLC)
High Resolution Inpainting with a Machine-learned Augmentation Model and Texture Transfer
Organization Name
Inventor(s)
Noritsugu Kanazawa of Campbell CA (US)
Neal Wadhwa of Cambridge MA (US)
Yael Pritch Knaan of Tel Aviv (IL)
High Resolution Inpainting with a Machine-learned Augmentation Model and Texture Transfer
This abstract first appeared for US patent application 18949447 titled 'High Resolution Inpainting with a Machine-learned Augmentation Model and Texture Transfer
Original Abstract Submitted
Systems and methods for augmenting images can utilize one or more image augmentation models and one or more texture transfer blocks. The image augmentation model can process input images and one or more segmentation masks to generate first output data. The first output data and the one or more segmentation masks can be processed with the texture transfer block to generate an augmented image. The input image can depict a scene with one or more occlusions, and the augmented image can depict the scene with the one or more occlusions replaced with predicted pixel data.