why paper is 35MB?
First-Person Hyper-lapse Videos
121–130 of 184 posts
Re: First-Person Hyper-lapse Videos
#122Pretty cool that they've included the raw video. Everyone can use that to compare their alternative method to the microsoft researchers' results.
Re: First-Person Hyper-lapse Videos
#123The videos don't load for me (due to mixed content, I believe), so here they are: https://www.youtube.com/watch?v=SOpwHaQnRSY https://www.youtube.com/watch?v=sA4Za3Hv6ng The hyperlapse of the climbing video looks like an FPS game from a decade ago with texture refreshing as you get closer.
Hi spindritf -- I work for YouTube and have been looking into some mixed content issues with embeds. Mind if I email you and ask for some details about this scenario?
Re: First-Person Hyper-lapse Videos
#124I'm surprised Microsoft never releases anything cool like that to their app store.
>We are working hard on making our Hyperlapse algorithm available as a Windows app. Stay tuned!
Ah cool. Over the years Microsoft Research has also released demos of other cool stuff, like recreating a 3d view using multiple photos from different angles. How about those projects?
Re: First-Person Hyper-lapse Videos
#125The 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…
You think a week of post end processing? I didn't read the paper or anything so I could be way off base, but I would assume the algo simply has to choose which frames to keep and which to toss. I doubt this would take an enormous amount of time even with HD videos. The algo is most likely just really clever in how it chooses a good frame vs a bad one. On the other hand, if it is actually generating a lot of "best gue…
The paper says it took 23,700 minutes to do just the frame selection for the 13 minute bike input video. That's over two weeks.
Re: First-Person Hyper-lapse Videos
#126If the MSR researchers are here -- I'm curious what does it look like when bordering hyperlapse with regular input? i.e., if there were a video consisting of input frames at the beginning and the end, with a stretch of hyperlapse in the middle, what does the transition look like? Does it need much smoothing? Also you probably saw this over the past week: http://jtsingh.com/index.php?route=information/information&i...…
The authors are at Siggraph in Vancouver this week, just saw them today. Likely they are too busy to read this thread today or tomorrow.
Re: First-Person Hyper-lapse Videos
#127If the MSR researchers are here -- I'm curious what does it look like when bordering hyperlapse with regular input? i.e., if there were a video consisting of input frames at the beginning and the end, with a stretch of hyperlapse in the middle, what does the transition look like? Does it need much smoothing? Also you probably saw this over the past week: http://jtsingh.com/index.php?route=information/information&i...…
Yes, I am here :-)
This would be possible. Although it would require providing some UI so the user could specify which parts should be sped up.
I've seen the Pjong Yang video, it is beautiful work. It requires very careful planning and shooting, and a lot of manual work to create such nice results. We're trying to make this easier for CASUAL, but it's still FAR away from the quality of professional hyperlapse.
Re: First-Person Hyper-lapse Videos
#128Bloody 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?
A desktop app, yes.
Re: First-Person Hyper-lapse Videos
#129Great 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.
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).
Re: First-Person Hyper-lapse Videos
#130I would use this for sure. I do timelapses of runs I do and set as challenges for our social running group. The source is a head-mounted GoPro.
The problem with them is that a straight forward pick-every-nth-frame gives a motion-sickness inducing video, as well as blurry. If you could extract the frame from the top of each stride when the camera is most steady, I would imagine it would be very much more watchable.