Hierarchical Feature Fusion CNN: Fast Intra Prediction Mode Decision for VVC Screen Content Coding

Versatile Video Coding (VVC) inherits Screen Content Coding (SCC) tools such as Intra Block Copy (IBC) and Palette mode (PLT) from High Efficiency Video Coding Screen Content Coding (HEVC-SCC), which is known as VVC-SCC. VVC-SCC can effectively improve the efficiency of screen content encoding, but it can also lead to higher encoding complexity. In order to reduce the encoding complexity of VVC-SCC, we design a Hierarchical Feature Fusion Convolutional Neural Network (HFF-CNN) for predicting the current CU best intra prediction mode. The encoder determines the current CU intra prediction mode based on the network out put best prediction mode, angle intra prediction mode indexes, and adjacent CU mode probability, skipping unnecessary rate distortion cost calculations and speeding up the encoding process. Experimental results show that the proposed model reduces the intra frame encoding time of VCC-SCC by 36.6% while increasing the average BDBR by 0.44%. Compared to state-of-the-art algorithms, it exhibits a better balance between the rate distortion performance and the encoding complexity.