A GoPro timelapse is also called a prolapse.
How unfortunate. http://en.wikipedia.org/wiki/Prolapse
First-Person Hyper-lapse Videos
171–180 of 184 posts
Re: First-Person Hyper-lapse Videos
#172The 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…
The technology is already available via photosynth: http://photosynth.net/preview/view/df869f96-2765-4939-8eb3-2... It appears that what they're doing here is simply extracting keyframes from the video, using them to compose a photosynth, then converting the autoplay of the synth to a video. If you load a photosynth and press "c", you can even see a the same point clouds and scene reconstruction seen on the research…
To me it seems like they are just taking frames subject to three constraints: average must be one every 10 frames, maximum gap must be say 80 frames, and finally the aggregate distance is minimized. In other words minimizing that metric subject to those two constraints. That's all. It's a nonlinear minimization problem.
EDIT: After reading their description, I agree they are going the photosynth route. Why not, they have the technology that you worked on. And they say that the naive subsampling I described above doesn't work...
Re: First-Person Hyper-lapse Videos
#173Earlier quoted context omitted.
It's striking but it's far more believable when you realize that they need to play at a much faster speed than the source, so they have tons of extra samples from which to extract information. They basically use all that data in the extra frames (that would otherwise simply get tossed away in a regular time-lapse) to construct a 3D scene. This wouldn't look nearly as good if they had to play it at normal speed.
"This wouldn't look nearly as good if they had to play it at normal speed." For normal speed you wouldn't need this :)
This technique actually works great for normal speed and can mimic the smoothness of a cinematographer's expensive dolly: https://www.youtube.com/watch?v=3TlCGh5Pc90
Re: First-Person Hyper-lapse Videos
#174i would pay to have that on a video player fast forward feature.
Re: First-Person Hyper-lapse Videos
#175The 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.
Hmm... Did I not embed these correctly? The project page as well as the embed links are plain http:// this is what it should be, no?
As mentioned in another comment, we recommend using schema-less embeds, e.g. "//www.youtube.com/embed/...". Regardless, these embeds should still work when embedded over HTTP.
Re: First-Person Hyper-lapse Videos
#176Earlier quoted context omitted.
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?
Re: First-Person Hyper-lapse Videos
#177Very excited about this being released as a product. HURRY UP!
Re: First-Person Hyper-lapse Videos
#178If 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.
It would be cool to mark segments for different speeds of hyperlapse, or normal input. Thinking about that I see what you are saying about a casual product. Anything beyond a uniform render becomes complicated. People would want to tweak the knobs and see the results, so possibly a faster "preview" algo that allows you to see the timings. Or a feature to quickly render just the (t-N, t+N) around the borders.
Re: First-Person Hyper-lapse Videos
#179Szeliski also has written a comprehensive Computer Vision book for those looking to learn the field. It's a fairly good one (and available for free online - http://szeliski.org/Book/).
Re: First-Person Hyper-lapse Videos
#180Earlier quoted context omitted.
time is kind of an essential component to music...
Time is supposed to be essential to video as well. This video http://vimeo.com/13669078 has time-lapsed audio. I wonder what it would sound like using the hyperlapse effect.
This is intriguing. What would you need to model as a the continuous input to try and get from the timelapse? With the imagery, a model was made of the 3D scene in which was then used for the 2D final output.
I'm having difficulty imagining what this more in-depth model would represent, and how you'd either strategically take the clips to "paint" this model.