Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence

arXiv:2404.13605v1 Announce Type: new
Abstract: Tackling image degradation due to atmospheric turbulence, particularly in dynamic environment, remains a challenge for long-range imaging systems. Existing techniques have been primarily designed for static scenes or scenes with small motion. This paper presents the first segment-then-restore pipeline for restoring the videos of dynamic scenes in turbulent environment. We leverage mean optical flow with an unsupervised motion segmentation method to separate dynamic and static scene components prior to restoration. After camera shake compensation and …

abstract arxiv challenge cs.cv dynamic eess.iv environment image imaging paper pipeline restore segment small systems turbulence type videos