IVCVMar 3, 2023

MAEVI: Motion Aware Event-Based Video Frame Interpolation

arXiv:2303.02025v11 citationsh-index: 27Has Code
Originality Incremental advance
AI Analysis

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes