DeepAI
Log In Sign Up

Complexity Reduction of Learned In-Loop Filtering in Video Coding

03/16/2022
by   Woody Bayliss, et al.
1

In video coding, in-loop filters are applied on reconstructed video frames to enhance their perceptual quality, before storing the frames for output. Conventional in-loop filters are obtained by hand-crafted methods. Recently, learned filters based on convolutional neural networks that utilize attention mechanisms have been shown to improve upon traditional techniques. However, these solutions are typically significantly more computationally expensive, limiting their potential for practical applications. The proposed method uses a novel combination of sparsity and structured pruning for complexity reduction of learned in-loop filters. This is done through a three-step training process of magnitude-guidedweight pruning, insignificant neuron identification and removal, and fine-tuning. Through initial tests we find that network parameters can be significantly reduced with a minimal impact on network performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/28/2020

Efficient Adaptation of Neural Network Filter for Video Compression

We present an efficient finetuning methodology for neural-network filter...
06/11/2020

Interpreting CNN for Low Complexity Learned Sub-pixel Motion Compensation in Video Coding

Deep learning has shown great potential in image and video compression t...
05/16/2018

A practical convolutional neural network as loop filter for intra frame

Loop filters are used in video coding to remove artifacts or improve per...
05/10/2019

Dynamically Expanded CNN Array for Video Coding

Video coding is a critical step in all popular methods of streaming vide...
02/26/2022

Symmetric Convolutional Filters: A Novel Way to Constrain Parameters in CNN

We propose a novel technique to constrain parameters in CNN based on sym...
10/14/2022

Neural Network Compression by Joint Sparsity Promotion and Redundancy Reduction

Compression of convolutional neural network models has recently been dom...
06/24/2021

A Global Appearance and Local Coding Distortion based Fusion Framework for CNN based Filtering in Video Coding

In-loop filtering is used in video coding to process the reconstructed f...