公开(公告)号：EP3709213A1

公开(公告)日：2020-09-16

申请号：EP20160923.7

申请日：2020-03-04

申请人： Nvidia Corporation

发明人： KIM, Joohwan ,  STENGEL, Michael ,  MAJERCIK, Zander ,  DE MELLO, Shalini ,  LAINE, Samuli ,  MCGUIRE, Morgan ,  LUEBKE, David

IPC分类号： G06K9/00 ,  G06K9/62

摘要： One embodiment of a method includes calculating one or more activation values of one or more neural networks trained to infer eye gaze information based, at least in part, on eye position of one or more images of one or more faces indicated by an infrared light reflection from the one or more images.

公开(公告)号：EP3731145A1

公开(公告)日：2020-10-28

申请号：EP20168957.7

申请日：2020-04-09

申请人： NVIDIA Corporation

发明人： PARK, Seonwook ,  DE MELLO, Shalini ,  MOLCHANOV, Pavlo ,  IQBAL, Umar ,  KAUTZ, Jan

IPC分类号： G06K9/62

摘要： A neural network is trained to identify one or more features of an image. The neural network is trained using a small number of original images, from which a plurality of additional images are derived. The additional images generated by rotating and decoding embeddings of the image in a latent space generated by an autoencoder. The images generated by the rotation and decoding exhibit changes to a feature that is in proportion to the amount of rotation.

公开(公告)号：EP3716150A1

公开(公告)日：2020-09-30

申请号：EP20164881.3

申请日：2020-03-23

申请人： Nvidia Corporation

发明人： VORONTSOV, Eugene ,  BYEON, Wonmin ,  DE MELLO, Shalini ,  JAMPANI, Varun ,  LIU, Ming-Yu ,  MOLCHANOV, Pavlo

IPC分类号： G06K9/62 ,  G06K9/32

摘要： The neural network includes an encoder, a common decoder, and a residual decoder. The encoder encodes input images into a latent space. The latent space disentangles unique features from other common features. The common decoder decodes common features resident in the latent space to generate translated images which lack the unique features. The residual decoder decodes unique features resident in the latent space to generate image deltas corresponding to the unique features. The neural network combines the translated images with the image deltas to generate combined images that may include both common features and unique features. The combined images can be used to drive autoencoding. Once training is complete, the residual decoder can be modified to generate segmentation masks that indicate any regions of a given input image where a unique feature resides.