Video inpainting detection and localization using inconsistencies in optical flow

In this paper we present a passive novel approach to detect and temporally localize video inpainting forgery based on optical flow consistency. The proposed algorithm comprises of two stages. In the first step, it detects whether the given video is inpainted or authentic using optical flow and in the second step temporal localization is performed. In order to evaluate the robustness of the proposed algorithm, experiments are performed against two popular and efficient inpainting techniques. We test our algorithm on comprehensive public datasets like PETS and SULFA. Experiments show that our approach is effective in detecting two popular inpainting types with good accuracy.