A QP-adaptive Mechanism for CNN-based Filter in Video Coding
This work addresses the inefficiency of multiple models for different QP bands in video coding, offering a more parameter-efficient solution for video compression applications.
The paper tackles the problem of needing separate CNN-based filter models for each quantization parameter (QP) band in video coding by introducing a QP-adaptive mechanism that incorporates quantization step into convolution, achieving better performance with only 25% of parameters and an additional 0.2% BD-rate reduction for chroma components.
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.