Video frame interpolation utilizing phase information

Abstract

Videos with low frame rate lacks the visual quality element and unable to meet the standards of new multimedia systems. Our goal is to develop an algorithm which interpolate the intermediate frame between two existing frames. Due to technology advancement, many algorithms have been proposed. Yet there is a requirement for efficient and reliable technique that can produce visually appealing interpolated frame. In this thesis, a technique for frame interpolation utilizing phase information is proposed. Phase information gives the intuition that the motion of signals can be depicted as a phase shift. Video frames may inherent noise due to change in illumination or because of camera jittering. The two consecutive input frames of video are passed through a guided filter to preserve edges of objects in frames. These frames then decompose into multi scale pyramid and the difference in each pixel is calculated to compute the phase difference which then used to interpolate the in-between frame. The proposed technique can be used to increase the frame rate of videos. Subjective and objective comparison is performed with the state of art existing technique to prove the significance of proposed technique. Experimental results reveal that the proposed technique is efficient and more accurate as compared to state of art frame interpolation technique.