Simone Meyer

TL;DR: In this article, a neural network decoder is proposed to directly estimate the phase decomposition of the intermediate frame, which is superior to the hand-crafted heuristics previously used in phase-based methods and also compares favorably to recent deep learning based approaches for video frame interpolation on challenging datasets.

TL;DR: This work proposes a deep learning framework for color propagation that combines a local strategy, to propagate colors frame-by-frame ensuring temporal stability, and a global strategy, using semantics for color propagate within a longer range.

TL;DR: In this article, a deep learning framework for color propagation in videos is proposed that combines a local strategy, to propagate colors frame-by-frame ensuring temporal stability, and a global strategy, using semantics for colour propagation within a longer range.

TL;DR: A novel phase-based method for propagating modifications of one video frame to an entire sequence by using the assumption that small motion can be represented as the phase shift of individual pixels and proposes a correction algorithm, which adapts thephase shift as well as the amplitude of the modified images.