MAEVI: Motion Aware Event-Based Video Frame Interpolation
arXiv:2303.02025
Abstract
Utilization of event-based cameras is expected to improve the visual quality of video frame interpolation solutions. We introduce a learning-based method to exploit moving region boundaries in a video sequence to increase the overall interpolation quality.Event cameras allow us to determine moving areas precisely; and hence, better video frame interpolation quality can be achieved by emphasizing these regions using an appropriate loss function. The results show a notable average \textit{PSNR} improvement of dB for the tested data sets, as well as subjectively more pleasing visual results with less ghosting and blurry artifacts.
Submitted to International Conference on Image Processing (ICIP) 2023