论文标题
CVEGAN：一种受感知风格的GAN，用于压缩视频增强
CVEGAN: A Perceptually-inspired GAN for Compressed Video Enhancement
论文作者
论文摘要
我们提出了一个新的生成对抗网络，用于压缩视频质量增强（CVEGAN）。 CVEGAN发电机受益于使用新型MUL2RES块（具有多个级别的残留学习分支），增强的残留非本地块（ERNB）和增强的卷积块注意模块（射精）。 ERNB也已被用于歧视者来提高代表性能力。 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.提出的网络已在两个典型的视频压缩增强工具的背景下进行了充分评估：后处理（PP）和空间分辨率适应（SRA）。在现有的最新的，在多个数据集的编码工具上，CVEGAN已完全集成到MPEG HEVC视频编码测试模型（HM16.20）中，实验结果表明，与锚定工具相比，在现有的最新架构中，跨多个数据组的编码工具显示了显着的编码增长（与锚相比，SRA最高28％，而SRA的编码增长率为38％）。
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.
