FastRIFE: Optimization of Real-Time Intermediate Flow Estimation for Video Frame Interpolation

The problem of video inter-frame interpolation is an essential task in the\nfield of image processing. Correctly increasing the number of frames in the\nrecording while maintaining smooth movement allows to improve the quality of\nplayed video sequence, enables more effective compression and creating a\nslow-motion recording. This paper proposes the FastRIFE algorithm, which is\nsome speed improvement of the RIFE (Real-Time Intermediate Flow Estimation)\nmodel. The novel method was examined and compared with other recently published\nalgorithms. All source codes are available at\nhttps://gitlab.com/malwinq/interpolation-of-images-for-slow-motion-videos\n