Performance Evaluation of CAIN Model Frame Interpolation Using Training Data Limited by Fixed Camera Scene Detection

Hikaru Usami, Yusuke Kameda

Abstract: We show that a limited dataset with fixed camera scene detection and a specific frame extraction method contribute to efficient training of the CAIN model for frame interpolation. Specifically, we use the detection of the scene of fixed cameras and the training dataset limited by several conditions, i.e., the condition of triplet consecutive frame extraction.