MAEVI: Motion Aware Event-Based Video Frame Interpolation
This work addresses video quality enhancement for applications like slow-motion video or surveillance, but it is incremental as it builds on existing event-based interpolation methods.
The paper tackled video frame interpolation by using event-based cameras to precisely identify moving regions, resulting in a 1.3 dB average PSNR improvement and reduced ghosting and blur artifacts.
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 $1.3$ dB for the tested data sets, as well as subjectively more pleasing visual results with less ghosting and blurry artifacts.