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.