Nokia Technologies Oy

Caglar Aytekin

Francesco Cricri

Miska Matias Hannuksela

Xingyang Ni

Emre Baris Aksu

Jani Lainema

Antti Hallapuro

Mikko Johannes Honkala

Miika Sakari Tupala

Francesco Cricrì

Ramin Ghaznavi Youvalari

Yat Hong Lam

Miika Tupala

The embodiments relate to a method comprising compressing input data (I) by means of at least a neural network (E,); determining a compression rate for data compression; miming the neural network (E,) with the input data (I) to produce an output data (c); removing a number of elements from the output data (c) according to the compression rate to result in a reduced form of the output data (me); and providing the reduced form of the output data (me) and the compression rate to a decoder (D,). The embodiments also relate to a method comprising receiving input data (me) for decompression; decompressing the input data (me) by means of at least a neural network (D,); determining a decompression rate for decompressing the input data (me); miming the neural network (D,) with input data (me) to produce a decompressed output data (ĩ); padding a number of elements to the compressed input data (me) according to the decompression rate to produce an output data (ĩ); and providing the output data (ĩ).

Method, an apparatus and a computer program product for video encoding and video decoding

A method comprising: obtaining (), in a first apparatus (), media content, encoding (), in a neural data compression network of the first apparatus (), the media content wherein one or more parameters of the neural data compression network are determined based on a type of at least one analysis task to be performed on the media content; and transmitting () the encoded media content to a second apparatus ().

Apparatus, a method and a computer program for running a neural network

A method comprising: obtaining a configuration of at least one neural network comprising a plurality of intra-prediction mode agnostic layers and one or more intra-prediction mode specific layers, the one or more intra-prediction mode specific layers corresponding to different intra-prediction modes; obtaining at least one input video frame comprising a plurality of blocks; determining to encode one or more blocks using intra prediction; determining an intra-prediction mode for each of said one or more blocks; grouping blocks having same intra-prediction mode into groups, each group being assigned with a computation path among the plurality of intra-prediction mode agnostic and the one or more intra-prediction mode specific layers; training the plurality of intra-prediction mode agnostic and/or the one or more intra-prediction mode specific layers of the neural networks based on a training loss between an output of the neural networks relating to a group of blocks and ground-truth blocks, wherein the ground-truth blocks are either blocks of the input video frame or reconstructed blocks; and encoding a block using a computation path assigned to an intra-prediction mode for the block.

Apparatus, a method and a computer program for video coding and decoding

Media content is received for streaming to a user device. A neural network is trained based on a first portion of the media content. Weights of the neural network are updated to overfit the first portion of the media content to provide a first overfitted neural network. The neural network or the first overfitted neural network is trained based on a second portion of the media content. Weights of the neural network or the first overfitted neural network are updated to overfit the second portion of the media content to provide a second overfitted neural network. The first portion and the second portion of the media content are sent with associations to the first overfitted neural network and the second overfitted to the user equipment.

Content-specific neural network distribution

A method, apparatus, and computer program product are provided for training a neural network or providing a pre-trained neural network with the weight-updates being compressible using at least a weight-update compression loss function and/or task loss function. The weight-update compression loss function can comprise a weight-update vector defined as a latest weight vector minus an initial weight vector before training. A pre-trained neural network can be compressed by pruning one or more small-valued weights. The training of the neural network can consider the compressibility of the neural network, for instance, using a compression loss function, such as a task loss and/or a weight-update compression loss. The compressed neural network can be applied within a decoding loop of an encoder side or in a post-processing stage, as well as at a decoder side.

Compressing weight updates for decoder-side neural networks

Video data is obtained or received. At least a current frame or previous frame(s) of the obtained or received video data are provided to an input of a neural network. A predicted output is generated at an output of the neural network. The predicted output includes at least one of predicted future frame(s) of the video data and predicted properties of future frame(s) of the video data. Processing decision(s) are determined based, at least in part, on the predicted output. The current frame of the video data is processed at least partially according to the processing decision(s).

Future video prediction for coding and streaming of video

A method, apparatus and computer program product provide an automated neural network training mechanism. The method, apparatus and computer program product receive a decoded noisy image and a set of input parameters for a neural network configured to optimize the decoded noisy image. A denoised image is generated based on the decoded noisy image and the set of input parameters. A denoised noisy error is computed representing an error between the denoised image and the decoded noisy image. The neural network is trained using the denoised noisy error and the set of input parameters and a ground truth noisy error value is received representing an error between the original image and the encoded image. The ground truth noisy error value is compared with the denoised noisy error to determine whether a difference between the ground truth noisy error value and the denoised noisy error is within a pre-determined threshold.

Growing community of inventors

Tampere, Finland

Caglar Aytekin