Abstract: Highlights•To the best of our knowledge, the proposed GCN-based fast CU partition network is the first attempt to apply the idea of image segmentation to the CU partition.•The proposed method can achieve tradeoffs between the coding performance and the computational complexity with different strategies according to the preferences of users.•Experimental results have demonstrated that the proposed method outperforms the state-of-the-art fast CU partition methods and the original VVenC 1.0 at the presets slow and medium.
Loading