A comprehensive survey on video frame interpolation techniques

Video frame interpolation is an important area in the computer vision research activities for video post-processing, surveillance, and video restoration tasks. It aims toward increasing the frame rate of a video sequence by calculating intermittent frames between consecutive input frames. This ensures extra smooth, clear motion in order to make animation fluid enough and reduce display motion blur. Advanced deep learning algorithms have the potential to discover knowledge from large-scale diverse video data. These algorithms gain insights about intermediate motion and provide new opportunities to further improve video interpolation technologies. This survey demonstrates a comprehensive overview of about a good number of contributions over past decade pertinent to the latest developments in this domain. The survey paper highlights common challenges in the area of video frame interpolation based on three key aspects: high visual quality, low complexity, and high efficiency of interpolated output from regular videos with the standard frame rate. We scrutinize the architectures, workflows, performance, advantages, and disadvantages and generate a broad categorization along with an overview of experimental results of various state-of-the-art methods executed on benchmark datasets. This survey discusses applications of diverse interpolation frameworks. It provides a backbone reference that inspires future researchers to optimize current techniques on academic and industrial grounds.