Abstract: A video capture device may be encode a set of original pictures to create encoded video data, decode the encoded video data to create a set of reconstructed pictures, determine a subset of parameters to update from among a plurality of parameters of a post-processing filter network, including using the set of original pictures as ground truth and the set of reconstructed pictures as input to the post-processing filter network, update the subset of parameters to generate updated parameters, and send the encoded video data and the updated parameters to a playback device.

Abstract: A sender device includes a memory configured to store an image frame of a video. The device also includes one or more processors coupled to the memory and configured to obtain encoded image data representing the image frame. The one or more processors are also configured to send, to a recipient device, a bitstream including the encoded image data as part of the video communication and a modification indicator that indicates whether image modification is sender permitted or sender prohibited at the recipient device.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for machine learning. In an example method, Gaussian kernels parameterized by a plurality of parameters corresponding to a set of attributes is accessed. A set of norm values for the set of attributes is determined based on the set of parameters, and a noise measure is generated based on the set of norm values. A set of rendered images is generated based on the Gaussian kernels and the first noise measure. A set of losses is generated based on the set of rendered images, and the plurality of parameters is updated based on the set of losses. An output rendered image is generated based on the updated plurality of parameters for the Gaussian kernels.

Abstract: Systems and techniques are described herein for training a video preprocessor. For instance, a method for training a video preprocessor is provided. The method may include processing training video data using a video encoder-decoder to generate intermediate video data; processing the intermediate video data using the video preprocessor to generate output video data; determining a loss based on the output video data and the training video data; and adjusting parameters of the video preprocessor based on the loss, wherein the video preprocessor is configured to process video data to generate preprocessed video data and to provide the preprocessed video data to a video encoder.

Abstract: Systems and techniques are described for model training. In some aspects, a computing device can determine a batch list indicating a sequence of trainings for each step of a plurality of steps for training network parameters of a neural network model, wherein the sequence of trainings comprises at least one of one or more backward trainings or one or more forward trainings. The computing device can train, according to the batch list, the network parameters of the neural network model. In some aspects, a computing device can determine a backward gradient based on performing backward training of network parameters of a neural network model and can determine, based on the backward gradient, a scale for forward training of the network parameters of the neural network model. The computing device can apply the scale to the network parameters for forward training of the network parameters of the neural network model.

Abstract: A video capture device may be encode a set of original pictures to create encoded video data, decode the encoded video data to create a set of reconstructed pictures, determine a subset of parameters to update from among a plurality of parameters of a post-processing filter network, including using the set of original pictures as ground truth and the set of reconstructed pictures as input to the post-processing filter network, update the subset of parameters to generate updated parameters, and send the encoded video data and the updated parameters to a playback device.

Abstract: A device includes one or more processors configured to obtain a bitstream corresponding to an encoded version of an image frame. The one or more processors are also configured to, based on determining that the bitstream includes a virtual reference frame usage indicator, generate a virtual reference frame based on synthesis support data included in the bitstream. The one or more processors are further configured to generate a decoded version of the image frame based on the virtual reference frame.