Valid Information Guidance Network for Compressed Video Quality Enhancement

by   Xuan Sun, et al.

In recent years deep learning methods have shown great superiority in compressed video quality enhancement tasks. Existing methods generally take the raw video as the ground truth and extract practical information from consecutive frames containing various artifacts. However, they do not fully exploit the valid information of compressed and raw videos to guide the quality enhancement for compressed videos. In this paper, we propose a unique Valid Information Guidance scheme (VIG) to enhance the quality of compressed videos by mining valid information from both compressed videos and raw videos. Specifically, we propose an efficient framework, Compressed Redundancy Filtering (CRF) network, to balance speed and enhancement. After removing the redundancy by filtering the information, CRF can use the valid information of the compressed video to reconstruct the texture. Furthermore, we propose a progressive Truth Guidance Distillation (TGD) strategy, which does not need to design additional teacher models and distillation loss functions. By only using the ground truth as input to guide the model to aggregate the correct spatio-temporal correspondence across the raw frames, TGD can significantly improve the enhancement effect without increasing the extra training cost. Extensive experiments show that our method achieves the state-of-the-art performance of compressed video quality enhancement in terms of accuracy and efficiency.


page 1

page 4

page 8

page 9


Enhancing Quality for VVC Compressed Videos by Jointly Exploiting Spatial Details and Temporal Structure

In this paper, we propose a quality enhancement network for Versatile Vi...

Low Light Video Enhancement by Learning on Static Videos with Cross-Frame Attention

The design of deep learning methods for low light video enhancement rema...

Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domain

Video understanding usually requires expensive computation that prohibit...

Multi-Frame Quality Enhancement for Compressed Video

The past few years have witnessed great success in applying deep learnin...

Speeding Up Action Recognition Using Dynamic Accumulation of Residuals in Compressed Domain

With the widespread use of installed cameras, video-based monitoring app...

Enhancing HEVC Compressed Videos with a Partition-masked Convolutional Neural Network

In this paper, we propose a partition-masked Convolution Neural Network ...

Multi-Frame Quality Enhancement On Compressed Video Using Quantised Data of Deep Belief Networks

In the age of streaming and surveillance compressed video enhancement ha...

Please sign up or login with your details

Forgot password? Click here to reset