Live data from Hacker News

First-Person Hyper-lapse Videos

research.microsoft.com

31–40 of 184 posts

Re: First-Person Hyper-lapse Videos

#31
I wonder how far you can get by using a "naive" timelapse of selecting frames from the video, but being smarter about which frames you choose. Rather than just choosing every nth frame, try to choose visually consistent frames by making the intervals between the frames loose, then apply conventional stabilization after the fact.

Re: First-Person Hyper-lapse Videos

#32
post #17

Bloody amazing! Fantastic work! Release it. Release it soon. This is something that everyone would want. I see they have listed a Windows app coming. Is that Windows desktop app?

If I were them I would offer this as a web service: upload your video and have it converted for $1.

Re: First-Person Hyper-lapse Videos

#37
post #36

Stunning effect, can anyone help me see the practical or entertainment-value use? I'm also curious if anyone else got motion sickness while watching the video.

If I could just take out my iphone and lazily records a skateboard ride down manhattan, and then get this result, that would be incredibly compelling.

For a slightly more practical use this could be a tool to give people previews of hiking trails, tours, or routes they're about to take.

Re: First-Person Hyper-lapse Videos

#38

Great results but looks expensive. I wonder how many minutes of processing per minute of video.

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.

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

Re: First-Person Hyper-lapse Videos

#40

The result is quite simply breathtaking. It looks like something shot for a movie using a stabilised dollycam, the fact they were able to achieve the same thing using nothing but a GoPro, their software, and likely a week of post-processing on a high end desktop PC is simply amazing. I hope we see this technology actually become readily available. There might still be work to be done, but in general if they can repro…

It's certainly way better than the source video, but it's nothing close to what would come from a steadycam or dolly. You couldn't use this finished product in any kind of real production.

I wonder if you could apply it to higher-quality (i.e. already pretty stable) input to approach a steadycam though?
Post reply on HN