当前位置:
X-MOL 学术
›
arXiv.cs.MM
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
A Convolutional Neural Network-Based Low Complexity Filter
arXiv - CS - Multimedia Pub Date : 2020-09-06 , DOI: arxiv-2009.02733 Chao Liu, Heming Sun, Jiro Katto, Xiaoyang Zeng, and Yibo Fan
arXiv - CS - Multimedia Pub Date : 2020-09-06 , DOI: arxiv-2009.02733 Chao Liu, Heming Sun, Jiro Katto, Xiaoyang Zeng, and Yibo Fan
Convolutional Neural Network (CNN)-based filters have achieved significant
performance in video artifacts reduction. However, the high complexity of
existing methods makes it difficult to be applied in real usage. In this paper,
a CNN-based low complexity filter is proposed. We utilize depth separable
convolution (DSC) merged with the batch normalization (BN) as the backbone of
our proposed CNN-based network. Besides, a weight initialization method is
proposed to enhance the training performance. To solve the well known over
smoothing problem for the inter frames, a frame-level residual mapping (RM) is
presented. We analyze some of the mainstream methods like frame-level and
block-level based filters quantitatively and build our CNN-based filter with
frame-level control to avoid the extra complexity and artificial boundaries
caused by block-level control. In addition, a novel module called RM is
designed to restore the distortion from the learned residuals. As a result, we
can effectively improve the generalization ability of the learning-based filter
and reach an adaptive filtering effect. Moreover, this module is flexible and
can be combined with other learning-based filters. The experimental results
show that our proposed method achieves significant BD-rate reduction than
H.265/HEVC. It achieves about 1.2% BD-rate reduction and 79.1% decrease in
FLOPs than VR-CNN. Finally, the measurement on H.266/VVC and ablation studies
are also conducted to ensure the effectiveness of the proposed method.
中文翻译:
基于卷积神经网络的低复杂度滤波器
基于卷积神经网络 (CNN) 的滤波器在减少视频伪影方面取得了显着的性能。然而,现有方法的高度复杂性使其难以在实际使用中应用。在本文中,提出了一种基于CNN的低复杂度滤波器。我们利用深度可分离卷积 (DSC) 与批量归一化 (BN) 合并作为我们提出的基于 CNN 的网络的主干。此外,提出了一种权重初始化方法来提高训练性能。为了解决众所周知的帧间过度平滑问题,提出了帧级残差映射 (RM)。我们定量分析了一些主流方法,如基于帧级和块级的过滤器,并构建我们基于 CNN 的具有帧级控制的过滤器,以避免由块级控制引起的额外复杂性和人为边界。此外,设计了一个名为 RM 的新模块来从学习的残差中恢复失真。因此,我们可以有效地提高基于学习的滤波器的泛化能力,达到自适应滤波效果。此外,该模块非常灵活,可以与其他基于学习的过滤器结合使用。实验结果表明,我们提出的方法比 H.265/HEVC 实现了显着的 BD 速率降低。与 VR-CNN 相比,它实现了约 1.2% 的 BD-rate 降低和 79.1% 的 FLOP 降低。最后,对 H.
更新日期:2020-09-08
中文翻译:
基于卷积神经网络的低复杂度滤波器
基于卷积神经网络 (CNN) 的滤波器在减少视频伪影方面取得了显着的性能。然而,现有方法的高度复杂性使其难以在实际使用中应用。在本文中,提出了一种基于CNN的低复杂度滤波器。我们利用深度可分离卷积 (DSC) 与批量归一化 (BN) 合并作为我们提出的基于 CNN 的网络的主干。此外,提出了一种权重初始化方法来提高训练性能。为了解决众所周知的帧间过度平滑问题,提出了帧级残差映射 (RM)。我们定量分析了一些主流方法,如基于帧级和块级的过滤器,并构建我们基于 CNN 的具有帧级控制的过滤器,以避免由块级控制引起的额外复杂性和人为边界。此外,设计了一个名为 RM 的新模块来从学习的残差中恢复失真。因此,我们可以有效地提高基于学习的滤波器的泛化能力,达到自适应滤波效果。此外,该模块非常灵活,可以与其他基于学习的过滤器结合使用。实验结果表明,我们提出的方法比 H.265/HEVC 实现了显着的 BD 速率降低。与 VR-CNN 相比,它实现了约 1.2% 的 BD-rate 降低和 79.1% 的 FLOP 降低。最后,对 H.