A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding

Abstract

Lossy image and video compression algorithms yield visually annoying artifacts including blocking, blurring, and ringing, especially at low bit-rates. To reduce these artifacts, post-processing techniques have been extensively studied. Recently, inspired by the great success of convolutional neural network (CNN) in computer vision, some researches were performed on adopting CNN in post-processing, mostly for JPEG compressed images. In this paper, we present a CNN-based post-processing algorithm for High Efficiency Video Coding (HEVC), the state-of-the-art video coding standard. We redesign a Variable-filter-size Residue-learning CNN (VRCNN) to improve the performance and to accelerate network training. Experimental results show that using our VRCNN as post-processing leads to on average 4.6% bit-rate reduction compared to HEVC baseline. The VRCNN outperforms previously studied networks in achieving higher bit-rate reduction, lower memory cost, and multiplied computational speedup.

MMM 2017

References in corpus (1)

• Caffe: Convolutional Architecture for Fast Feature Embedding

Cited by in corpus (35)

• Image and Video Compression with Neural Networks: A Review
• MFQE 2.0: A New Approach for Multi-frame Quality Enhancement on Compressed Video
• Enhancing Quality for HEVC Compressed Videos
• Multi-Frame Quality Enhancement for Compressed Video
• DeepQTMT: A Deep Learning Approach for Fast QTMT-based CU Partition of Intra-mode VVC
• A DenseNet Based Approach for Multi-Frame In-Loop Filter in HEVC
• Deep Learning-Based Video Coding: A Review and A Case Study
• Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model
• Learning for Video Compression
• A Comprehensive Benchmark for Single Image Compression Artifacts Reduction
• Enhancing HEVC Compressed Videos with a Partition-masked Convolutional Neural Network
• MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering
• Partition-Aware Adaptive Switching Neural Networks for Post-Processing in HEVC
• A Convolutional Neural Network Approach for Half-Pel Interpolation in Video Coding
• MGANet: A Robust Model for Quality Enhancement of Compressed Video
• Recent Advances on HEVC Inter-frame Coding: From Optimization to Implementation and Beyond
• Combining Progressive Rethinking and Collaborative Learning: A Deep Framework for In-Loop Filtering
• B-DRRN: A Block Information Constrained Deep Recursive Residual Network for Video Compression Artifacts Reduction
• A practical convolutional neural network as loop filter for intra frame
• Non-Local ConvLSTM for Video Compression Artifact Reduction
• End-to-End Learned Image Compression with Quantized Weights and Activations
• A Convolutional Neural Network-Based Low Complexity Filter
• A QP-adaptive Mechanism for CNN-based Filter in Video Coding
• Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information
• PEA265: Perceptual Assessment of Video Compression Artifacts
• Efficient Integer-Arithmetic-Only Convolutional Neural Networks
• Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction
• Deep Reference Generation with Multi-Domain Hierarchical Constraints for Inter Prediction
• Multi-Density Attention Network for Loop Filtering in Video Compression
• Learned Quality Enhancement via Multi-Frame Priors for HEVC Compliant Low-Delay Applications
• Residual-Guided In-Loop Filter Using Convolution Neural Network
• Editorial: Introduction to the Issue on Deep Learning for Image/Video Restoration and Compression
• Dual Learning-based Video Coding with Inception Dense Blocks
• Enhancing Quality for VVC Compressed Videos by Jointly Exploiting Spatial Details and Temporal Structure
• NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results