CVEGAN：一种受感知启发的用于压缩视频增强的GAN
CVEGAN: A Perceptually-inspired GAN for Compressed Video Enhancement
AI总结：
本文提出CVEGAN，通过Mul2Res、ERNB、ECBAM及ReSphereGAN感知训练增强压缩视频，并在HM16.20的PP和SRA任务中取得显著编码增益。
摘要：
我们提出了一种用于压缩视频质量增强（Compressed Video quality Enhancement，CVEGAN）的新型生成对抗网络。CVEGAN生成器得益于采用了新颖的Mul2Res块（具有多级残差学习分支）、增强型残差非局部块（ERNB）和增强型卷积块注意力模块（ECBAM）。ERNB也被用于判别器中，以提升表征能力。训练策略也针对视频压缩应用进行了专门重新设计，采用了相对论球面GAN（ReSphereGAN）训练方法以及新的感知损失函数。所提出的网络已在两种典型视频压缩增强工具的场景中得到全面评估：后处理（PP）和空间分辨率适配（SRA）。CVEGAN已被完整集成到MPEG HEVC视频编码测试模型（HM16.20）中；实验结果表明，在多个数据集上，对于这两种编码工具，该网络相比现有最先进架构均取得了显著编码增益（与锚点相比，PP最高达28%，SRA最高达38%）。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
