Spatial and Temporal Interpolation of Multi-View Image Sequences

Abstract. We propose a simple and effective framework for multi-view image sequence interpolation in space and time. For spatial view point interpolation we present a robust feature-based matching algorithm that allows for wide-baseline camera configurations. To this end, we intro-duce two novel filtering approaches for outlier elimination and a robust approach for match extrapolations at the image boundaries. For small-baseline and temporal interpolations we rely on an established optical flow based approach. We perform a quantitative and qualitative evalua-tion of our framework and present applications and results. Our method has a low runtime and results can compete with state-of-the-art methods. Fig. 1: Spatial view point interpolation between two images. Our approach robustly handles wide-baseline view point interpolations. From left to right: source image, in-terpolation at t = 1/3, interpolation at t = 2/3, target image.