Abstract: A device may be configured to perform frame rate up sampling based on information included in a neural network post-filter characteristics message. In one example, the neural network post-filter characteristics message includes a syntax element specifying a number of input pictures to be used as input for a neural network post-filter picture interpolation process and a syntax element having a value specifying a manner in which input pictures are concatenated before being input into the neural network post-filter picture interpolation process.

Abstract: A device may be configured to signal neural network post-filter parameter information. In one example, a device signals a neural network post-filter characteristics message including a syntax element specifying a number of interpolated pictures generated by a post-processing filter between consecutive pictures used as input for the post-processing filter. In one example, a neural network post-filter characteristics message includes a syntax element specifying a number of decoded output pictures used as input for the post-processing filter.

Abstract: A method for training a neural network system for generating paired low resolution (LR) and high resolution (HR) images, the neural network system, an apparatus, and a non-transitory computer-readable storage medium thereof are provided. The method includes that a first generator in the neural network system generates a LR image based on a random vector; a second generator in the neural network system generates a HR image based on the random vector, where the HR image is paired with the LR image; obtaining a plurality of losses based on the LR image and the HR image; and updating the first generator based on the plurality of losses.

Abstract: A neural network system for restoring images, a method and a non-transitory computer-readable storage medium thereof are provided. The neural network system includes an encoder and a generative adversarial network (GAN) prior network. The encoder includes a plurality of encoder blocks, where each encoder block includes at least one transformer block and one convolution layer, where the encoder receives an input image and generates a plurality of encoder features and a plurality of latent vectors. Additionally, the GAN prior network includes a plurality of pre-trained generative prior layers, where the GAN prior network receives the plurality of encoder features and the plurality of latent vectors from the encoder and generates an output image with super-resolution.