From the paper listed on the page it looks like it takes about 305 hours to process a 10 minute video. The vast majority of that is during the "source selection" phase which takes 1 minute per frame of video.

We've already managed to dramatically reduce the processing time compared to the numbers reported in the paper.

It'll still be slow (a couple hours for a 10 min video) but running on a singe standard PC (with GPU).

It looks like after the frame-selection step, the rest of the process never refers to the discarded frames. Is that right? Do you think making the frames available for blending in the later steps would results in smoother blends?

Prediction: When Microsoft releases this as an app it will be heavily leveraged with Azure to create fast results. Especially if the bulk of the work is in the source selection which, I believe, can be easily done in parallel.

Throw a couple engineers solely at optimizing perf and I'm sure it could be brought down.

Yeah, they say so themselves in the paper:

> "In this work, we were more interested in building a proof- of-concept system rather than optimizing for performance. As a result, our current implementation is slow. It is difficult to measure the exact timings, as we distributed parts of the SfM reconstruction and source selection to multiple machines on a cluster. Table 2 lists an informal summary of our computation times. We expect that substantial speedups are possible by replacing the incremental SfM reconstruction with a real-time SLAM system [Klein and Murray 2009], and finding a faster heuristic for preventing selecting of oc- cluded scene parts in the source selection. We leave these speed-ups to future work."

Ouch. I'll be going on a long bike ride in a month, and I was wondering if I could generate a hyperlapse of it... but it's going to be at least four hours, which doesn't bode well.

Back of the envelope, i get 7680 frames to process, one minute each which is just under $1300 for a medium windows azure instance. Not cheap, but probably doable. I'd bet you could spend a few hours fiddling with large memory instances versus medium, and find a sweet spot.

Set aside $50-100 a month, it'll probably be a lot cheaper in a year. (assuming optimizations and cheaper cloud services)

Or you could just buy a computer and stick it in a corner running 24-7. After it has finished selecting/rendering, you have both a video and a computer you can use afterwards.

Yeah, I'm more likely to go with this option, rather than spend over a grand on a video that may end up looking like crap anyway.

Sounds like something that would be good for a cloud service to provide. Upload your video and let their farm of tuned servers churn on it for a while.

With an option to host it too, considering they can provide higher bitrates:- https://news.ycombinator.com/item?id=8160890

Upload video, generate hyperlapse, generate a URL and view the higher bitrate video on iPhone, Android or Windows. Considering GoPro/Drone videos generate lots of interest, this will be a very highly useful service.

But still cheaper than the specialist hardware and its operator... Probably.