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 (14)

• Image and Video Compression with Neural Networks: A Review
• Partition-Aware Adaptive Switching Neural Networks for Post-Processing in HEVC
• Recent Advances on HEVC Inter-frame Coding: From Optimization to Implementation and Beyond
• B-DRRN: A Block Information Constrained Deep Recursive Residual Network for Video Compression Artifacts Reduction
• Non-Local ConvLSTM for Video Compression Artifact Reduction
• A Convolutional Neural Network-Based Low Complexity Filter
• Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information
• 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
• Learned Quality Enhancement via Multi-Frame Priors for HEVC Compliant Low-Delay Applications
• NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results
• Enhancing Quality for VVC Compressed Videos by Jointly Exploiting Spatial Details and Temporal Structure
• Dual Learning-based Video Coding with Inception Dense Blocks