Hierarchical Representation of Videos with Spatio-Temporal Fibers

We propose a new representation of videos, as spatio- temporal fibers. These fibers are clusters of trajectories that are meshed spatially in the image domain. They form a hier- archical partition of the video into regions that are coherent in time and space. They can be seen as dense, spatially- organized, long-term optical flow. Their robustness to noise and ambiguities is ensured by taking into account the relia- bility of each source of information. As fibers allow users to handle easily moving objects in videos, they prove useful for video editing, as demonstrated in a video inpainting example.