Visual quality and algorithm efficiency are two main interests in video frame\ninterpolation. We propose a hybrid task-based convolutional neural network for fast and accurate\nframe interpolation of 4K videos. The proposed method synthesizes low-resolution frames, then\nreconstructs high-resolution frames in a coarse-to-fine fashion. We also propose edge loss, to\npreserve high-frequency information and make the synthesized frames look sharper. Experimental\nresults show that the proposed method achieves state-of-the-art performance and performs 2.69x\nfaster than the existing methods that are operable for 4K videos, while maintaining comparable\nvisual and quantitative quality.
Loading....