LAP-based motion-compensated frame interpolation

High-quality video frame interpolation often necessitates accurate motion estimates between consecutive frames. Standard video encoding schemes often estimate the motion between frames using variants of block matching algorithms. For the sole purposes of video frame interpolation, more accurate estimates can be obtained using modern optical flow methods. In this thesis, we use the recently proposed Local All-Pass (LAP) algorithm to compute the optical flow between two consecutive frames. The resulting flow field is used to perform interpolation using cubic splines. We compare the interpolation results against a well-known optical flow estimation algorithm as well as against a recent convolutional neural network scheme for video frame interpolation. Qualitative and quantitative results show that the LAP algorithm performs fast, high-quality video frame interpolation, and perceptually outperforms the neural network and the Lucas-Kanade method on a variety of test sequences. We also perform a case study to compare LAP interpolated frames against those obtained using two leading methods on the Middlebury optical flow benchmark. Finally, we perform a user study to gauge the correlation between the quantitative and qualitative results.Ope