Microsoft Research have been working on a way to convert First-person videos to a ‘smooth’ time-lapse even if they are roughly filmed and jerky. The video below demonstrates the extremely impressive algorithm that has been developed to smooth out jerky footage and produce a super slick hyper-lapse video.
We present a method for converting first-person videos, for example, captured with a helmet camera during activities such as rock climbing or bicycling, into hyperlapse videos: time-lapse videos with a smoothly moving camera.
At high speed-up rates, simple frame sub-sampling coupled with existing video stabilization methods does not work, because the erratic camera shake present in first-person videos is amplified by the speed-up.
Our algorithm first reconstructs the 3D input camera path as well as dense, per-frame proxy geometries. We then optimize a novel camera path for the output video (shown in red) that is smooth and passes near the input cameras while ensuring that the virtual camera looks in directions that can be rendered well from the input.
The team also shared a video that demonstrates how they work-out the geometry of the movement with-in a video and then convert it into smoother motion:
Unfortunately there is no consumer version of this product yet but I personally can’t wait to try it out!