Convolutional neural network (CNN)-based filters have achieved great success in video coding. However, in most previous works, individual models are needed for each quantization parameter (QP) band. This paper presents a generic method to help an arbitrary CNN-filter handle different quantization noise. We model the quantization noise problem and implement a feasible solution on CNN, which introduces the quantization step (Qstep) into the convolution. When the quantization noise increases, the ability of the CNN-filter to suppress noise improves accordingly. This method can be used directly to replace the (vanilla) convolution layer in any existing CNN-filters. By using only 25% of the parameters, the proposed method achieves better performance than using multiple models with VTM-6.3 anchor. Besides, an additional BD-rate reduction of 0.2% is achieved by our proposed method for chroma components.
翻译:以进化神经网络(CNN)为基础的过滤器在视频编码方面取得了巨大成功。 但是,在大多数先前的工程中,每个量化参数(QP)带都需要单个模型。 本文提出了一个通用方法, 帮助一个专制CNN过滤器处理不同量化噪音。 我们模拟了量化噪音问题,并在CNN上实施了一个可行的解决方案, 从而将四分化步骤( Qstep)引入到进化中。 当量化噪音增加时, CNN过滤器抑制噪音的能力也相应提高。 这种方法可以直接用来取代任何现有的CNN过滤器中的( vanilla) 电动层。 仅使用25%的参数, 拟议的方法就比使用VTM-6.3锚的多个模型取得更好的性能。 此外, 我们提出的铬组件方法还实现了0.2%的BD率进一步降低。