The source videos they used as examples are about 600 frames each, which is ~40 seconds of video. For a politician or professional actor this would be easy to achieve. Likewise if you wanted a good 3d model of yourself or a friend you could do it cheaply using this method.
I may be misreading the paper, but as far as I understand you need a collection of photos in addition to the video.
I thought that too, but then they have some ambiguous sentences like 'In this paper we target high detail reconstruction from a single video captured in the wild, i.e., under uncontrolled imaging conditions,' where it seems as if they treat that as their input library. Other parts of the paper support your interpretation. It's annoyingly vague.
...but still, outstanding work even if it requires manual calibration like curation of the input set.
and judging by their selection of subjects, I would presume the accompanying photo library would need to be quite large.