Back to results
US 2022/0103845 A1Published application
Activation function design in neural network-based filtering process for video coding
AssigneeQUALCOMM Incorporated
InventorsHongtao Wang, Jianle Chen, Marta Karczewicz
Life of this patent
Estimating the term…
Abstract
A method of coding video data, the method comprising: reconstructing a block of the video data; and applying a Convolutional Neural Network (CNN)-based filter to the reconstructed block, wherein the CNN-based filter uses a LeakyReLU activation function.
Claims30
A method of encoding or decoding video data, the method comprising:
- reconstructing a block of the video data;
- and
- applying a Convolutional Neural Network (CNN)-based filter to the reconstructed block, wherein the CNN-based filter uses a LeakyReLU activation function.
A device for encoding or decoding video data, the device comprising:
- a memory to store the video data;
- and
- one or more processors implemented in circuitry, the one or more processors configured to:
- reconstruct a block of the video data;
- and
- apply a Convolutional Neural Network (CNN)-based filter to the reconstructed block, wherein the CNN-based filter uses a LeakyReLU activation function.
3 more elements
A device for encoding or decoding video data, the device comprising:
- means for reconstructing a block of the video data;
- and
- means for applying a Convolutional Neural Network (CNN)-based filter to the reconstructed block, wherein the CNN-based filter uses a LeakyReLU activation function.
A computer-readable storage medium having stored thereon instructions that, when executed, cause one or more processors to:
- reconstruct a block of video data;
- and
- apply a Convolutional Neural Network (CNN)-based filter to the reconstructed block, wherein the CNN-based filter uses a LeakyReLU activation function.
Dependencies are inferred from the claim text.