Learning Robust Video Synchronization without Annotations
This addresses a fundamental unsolved problem in computer graphics and vision for applications requiring video alignment, though it appears incremental as it builds on previous methods by extending to longer time gaps.
The paper tackles the problem of aligning video sequences without manual annotations by presenting a scalable, robust method that autonomously manages training data in an iterative procedure. The result is a system capable of aligning videos recorded months apart, overcoming limitations of previous methods that handle only similar conditions like weather or illumination.
Aligning video sequences is a fundamental yet still unsolved component for a broad range of applications in computer graphics and vision. Most classical image processing methods cannot be directly applied to related video problems due to the high amount of underlying data and their limit to small changes in appearance. We present a scalable and robust method for computing a non-linear temporal video alignment. The approach autonomously manages its training data for learning a meaningful representation in an iterative procedure each time increasing its own knowledge. It leverages on the nature of the videos themselves to remove the need for manually created labels. While previous alignment methods similarly consider weather conditions, season and illumination, our approach is able to align videos from data recorded months apart.