CVEGAN: A Perceptually-inspired GAN for Compressed Video Enhancement
arXiv:2011.09190 · doi:10.1016/j.image.2024.117127
Abstract
We propose a new Generative Adversarial Network for Compressed Video quality Enhancement (CVEGAN). The CVEGAN generator benefits from the use of a novel Mul2Res block (with multiple levels of residual learning branches), an enhanced residual non-local block (ERNB) and an enhanced convolutional block attention module (ECBAM). The ERNB has also been employed in the discriminator to improve the representational capability. The training strategy has also been re-designed specifically for video compression applications, to employ a relativistic sphere GAN (ReSphereGAN) training methodology together with new perceptual loss functions. The proposed network has been fully evaluated in the context of two typical video compression enhancement tools: post-processing (PP) and spatial resolution adaptation (SRA). CVEGAN has been fully integrated into the MPEG HEVC video coding test model (HM16.20) and experimental results demonstrate significant coding gains (up to 28% for PP and 38% for SRA compared to the anchor) over existing state-of-the-art architectures for both coding tools across multiple datasets.
References in corpus (8)
- Image and Video Compression with Neural Networks: A Review
- ResNeSt: Split-Attention Networks
- M-LVC: Multiple Frames Prediction for Learned Video Compression
- BVI-DVC: A Training Database for Deep Video Compression
- MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering
- Partition-Aware Adaptive Switching Neural Networks for Post-Processing in HEVC
- Video Compression with CNN-based Post Processing
- Perceptually Optimizing Deep Image Compression
Cited by in corpus (6)
- BVI-AOM: A New Training Dataset for Deep Video Compression Optimization
- Compressing Deep Image Super-resolution Models
- RTSR: A Real-Time Super-Resolution Model for AV1 Compressed Content
- RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content
- RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment
- Enhancing HDR Video Compression through CNN-based Effective Bit Depth Adaptation