Omnidirectional videos that capture the entire surroundings are employed in a variety of fields such as VR applications and remote sensing. However, their wide field of view makes it easy for unwanted objects to appear in the videos. This problem can be addressed by video inpainting, which enables the natural removal of such objects while preserving both spatial and temporal consistency. Nevertheless, most existing methods assume processing ordinary videos with a narrow field of view and do not tackle the distortion in equirectangular projection of omnidirectional videos. To address this issue, this paper proposes a novel deep learning model for omnidirectional video inpainting, called Distortion-Aware Omnidirectional Video Inpainting (DAOVI). DAOVI introduces a module that evaluates temporal motion information in the image space considering geodesic distance, as well as a depth-aware feature propagation module in the feature space that is designed to address the geometric distortion inherent to omnidirectional videos. The experimental results demonstrate that our proposed method outperforms existing methods both qualitatively and quantitatively.
@misc{Seshimo2025DAOVI,
author={Ryosuke Seshimo and Mariko Isogawa},
title={DAOVI: Distortion-Aware Omnidirectional Video Inpainting},
year={2025},
eprint={2509.00396},
archivePrefix={arXiv}
}