基于卷积神经网络的低复杂度滤波器
A Convolutional Neural Network-Based Low Complexity Filter
摘要：
基于卷积神经网络（CNN）的滤波器在视频伪影减少方面取得了显著的性能。然而，现有方法的高度复杂性使得其难以在实际应用中得到应用。本文提出了一种基于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的网络的骨干。此外，提出了一种权重初始化方法，以提高训练性能。为了解决帧间过平滑问题，提出了一种帧级残差映射（RM）。我们对一些主流的方法如基于帧级和块级的滤波器进行了定量分析，并构建了基于CNN的帧级控制滤波器，以避免块级控制带来的额外复杂性和人为边界。此外，一个新的模块称为RM的设计，以恢复从学习残差的失真。结果表明，可以有效地提高基于学习的滤波器的泛化能力，达到自适应滤波的效果。此外，该模块是灵活的，可以与其他基于学习的过滤器相结合。实验结果表明，我们提出的方法实现了显着的BD率降低比H.265/HEVC。与VR-CNN相比，它实现了约1.2%的BD速率降低和79.1%的FLOP降低。266/VVC上的测试和消融实验验证了该方法的有效性。
英文摘要：
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.
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。
