A Global Appearance and Local Coding Distortion based Fusion Framework for CNN based Filtering in Video Coding
Not on the map. Why?
Abstract (arXiv)
In-loop filtering is used in video coding to process the reconstructed frame in order to remove blocking artifacts. With the development of convolutional neural networks (CNNs), CNNs have been explored for in-loop filtering considering it can be treated as an image de-noising task. However, in addition to being a distorted image, the reconstructed frame is also obtained by a fixed line of block based encoding operations in video coding. It carries coding-unit based coding distortion of some similar characteristics. Therefore, in this paper, we address the filtering problem from two aspects, global appearance restoration for disrupted texture and local coding distortion restoration caused by fixed pipeline of coding. Accordingly, a three-stream global appearance and local coding distortion based fusion network is developed with a high-level global feature stream, a high-level local feature stream and a low-level local feature stream. Ablation study is conducted to validate the necessity of different features, demonstrating that the global features and local features can complement each other in filtering and achieve better performance when combined. To the best of our knowledge, we are the first one that clearly characterizes the video filtering process from the above global appearance and local coding distortion restoration aspects with experimental verification, providing a clear pathway to developing filter techniques. Experimental results demonstrate that the proposed method significantly outperforms the existing single-frame based methods and achieves 13.5%, 11.3%, 11.7% BD-Rate saving on average for AI, LDP and RA configurations, respectively, compared with the HEVC reference software.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 61 references that are in the map. First posted on arXiv 24 Jun 2021.
Builds on
27 of 61 references.
References · 27
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2018CBAM: Convolutional Block Attention Modulecited by 2,463
- 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
- 2018Unprocessing Images for Learned Raw Denoisingcited by 250
- 2018Residual Dense Network for Image Restorationcited by 181
- 2019Real Image Denoising with Feature Attentioncited by 176
- 2015Compression Artifacts Reduction by a Deep Convolutional Networkcited by 136
- 2015All you need is a good initcited by 124
15 more
- 2018Denoising Prior Driven Deep Neural Network for Image Restorationcited by 80
- 2014Deeply learned face representations are sparse, selective, and robustcited by 56
- 2018Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Networkcited by 51
- 2018Multi-Frame Quality Enhancement for Compressed Videocited by 48
- 2018Connecting Image Denoising and High-Level Vision Tasks via Deep Learningcited by 39
- 2016CAS-CNN: A Deep Convolutional Neural Network for Image Compression Artifact Suppressioncited by 33
- 2020Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Imagescited by 28
- 2016A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Codingcited by 26
- 2020MFRNet: A New CNN Architecture for Post-Processing and In-loop Filteringcited by 15
- 2019PixelRL: Fully Convolutional Network with Reinforcement Learning for Image Processingcited by 13
- 2019A DenseNet Based Approach for Multi-Frame In-Loop Filter in HEVCcited by 10
- 2018Enhancing HEVC Compressed Videos with a Partition-masked Convolutional Neural Networkcited by 8
- 2018MGANet: A Robust Model for Quality Enhancement of Compressed Videocited by 4
- 2019Enhancing Quality for VVC Compressed Videos by Jointly Exploiting Spatial Details and Temporal Structurecited by 4
- 2018A practical convolutional neural network as loop filter for intra framecited by 3
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 1.
2 papers.