Phase-Based Modification Transfer for Video


We present a novel phase-based method for propagating modifi cations of one video frame to an entire sequence.

September 15, 2016
European Conference on Computer Vision (ECCV) 2016



Simone Meyer (Disney Research/ETH Joint M.Sc.)

Alexander Sorkine-Hornung (Disney Research)

Markus Gross (Disney Research/ETH Zurich)

Phase-Based Modification Transfer for Video


Instead of computing accurate pixel correspondences between frames, e.g. extracting sparse features or optical flow, we use the assumption that small motion can be represented as the phase shift of individual pixels. In order to successfully apply this idea to transferring image edits, we propose a correction algorithm, which adapts the phase shift as well as the amplitude of the modi ed images. As our algorithm avoids expensive global optimization and all computational steps are performed per-pixel, it allows for a simple and ecient implementation. We evaluate the flexibility of the approach by applying it to various types of image modi cations, ranging from compositing and colorization to image fi lters.

Copyright Notice