Chroma Intra Prediction with attention-based CNN architectures
This work addresses video compression efficiency for video coding applications, representing an incremental improvement over existing neural network-based methods.
The paper tackles the problem of chroma intra-prediction in video coding by proposing a neural network architecture with a novel attention module to model spatial relations between reference and predicted samples, achieving compression gains over the latest VVC anchor compared to state-of-the-art neural network methods.
Neural networks can be used in video coding to improve chroma intra-prediction. In particular, usage of fully-connected networks has enabled better cross-component prediction with respect to traditional linear models. Nonetheless, state-of-the-art architectures tend to disregard the location of individual reference samples in the prediction process. This paper proposes a new neural network architecture for cross-component intra-prediction. The network uses a novel attention module to model spatial relations between reference and predicted samples. The proposed approach is integrated into the Versatile Video Coding (VVC) prediction pipeline. Experimental results demonstrate compression gains over the latest VVC anchor compared with state-of-the-art chroma intra-prediction methods based on neural networks.