Denser 3D Point Clouds in OpenSfM

http://blog.mapillary.com/update/2016/10/31/denser-3d-point-clouds-in-opensfm.html

by yubin • 10 years ago

117 36 10 years ago

blog.mapillary.com

Pica_soO• 10 years ago

Do they use the same NeuralNets that are used to improve videos on these pictures to reconstruct the details?

yummybear• 10 years ago

I wonder if you wouldn't get cleaner results if you eliminated points that don't have an adjacent point nearer than a certain distance?

yubin3• 10 years ago

Yes. We can apply different heuristics to remove outlier points. One interesting way to do it will be to train a neural network to refine the dense point cloud.

zubairq• 10 years ago

Pretty amazing stuff!!

washwash• 10 years ago

great

eriknstr• 10 years ago

Never heard of OpenSfM before but have been looking for something like it.

spacemanmatt• 10 years ago

I have personal and professional projects that involve mundane data feeding and service-building around this core capability. This totally fills a niche that's been on my tech radar for a while.

dharma12• 10 years ago

very cool. that's quite dense.

So the segmentation convnet is applied on the 2d image pixels before SfM, rather than on the point cloud data? I've been looking for neural net semantic segmentation for 3D point cloud data

yubin3• 10 years ago

Exactly, the convnet is applied on 2d pixels instead of on 3D point clouds. If one have labelled 3D points (e.g. if a point is part of a car or not), one can train a network for recognition directly on 3D points.

dharma12• 10 years ago

Nice. I wonder if this could be used for robot navigation. The segmented point clouds especially are useful.

Been looking forward to a DIY Roomba project using point clouds and neural nets for navigation

deckar013• 10 years ago

I discovered VisualSfM this weekend after trying Adobe ReCap 360. The photo reconstruction functionality of ReCap is cloud based, which was a blocker for me, because I have a beefy graphics rig and want to script it into a pipeline.

I am curious how OpenSfM compares to VisualSfM and if they are related in any way.

Edit: The VisualSfM license is only open for non-commercial uses. OpenSfM is BSD licensed, so I can safely build my business on top of it.

yubin3• 10 years ago

Both VisualSfM and OpenSfM use similar methodology (incremental structure from motion) to reconstruct 3D scene points and camera positions from photos.

And yes, you can build your own tools (even commercially) with OpenSfM.

deckar013• 10 years ago

I am curious how the quality compares and if they have common library dependencies.

yorwba• 10 years ago

I am curious, did you try to build VisualSfM yourself? I had to use it for a project at Uni a few years ago and the build process was quite adventurous, without this[0] guide I would have been completely lost. Would be interesting to know whether it has gotten any easier.

[0] http://www.10flow.com/2012/08/15/building-visualsfm-on-ubunt...

deckar013• 10 years ago

No, I used the windows binaries during evaluation.

exthaicitizen• 10 years ago

Adobe doesn't make ReCap 360, Autodesk does.

efkv• 10 years ago

For those who have not tried it, OpenSfM is an amazing tool. Can't wait to play with dense reconstructions. Congrats mapillary team, I know this has been a long time coming!

MichailP3• 10 years ago

Is it possible to use images from say Google Street View to reconstruct 3D city model with this tool? Maybe it could fall into fair use for small part of city...

maxerickson4• 10 years ago

It would likely violate their TOS.

No creation or augmentation of data sets based on Google’s Content or Services. You will not use Google’s Content or Services to create or augment your own mapping-related dataset (or that of a third party), including a mapping or navigation dataset, business listings database, mailing list, or telemarketing list.

There's probably some other issues.

https://developers.google.com/maps/terms

rasmi2• 10 years ago

You would need a significant number of images for a particular scene (more than Google Street View would provide -- maybe in the tens or hundreds depending on the complexity -- but perhaps mining Google Maps photo uploads for a particular location would suffice). A Google Image search for a particular landmark is likely to yield better results ([1], [2], [3]). Also, stitching together multiple scenes after reconstructing each individual scene may prove difficult. Apple Maps does a sort of satellite view projection on to 3D building models ([4]), but this is far from a dense reconstruction.

[1]http://grail.cs.washington.edu/projects/timelapse/

[2]http://grail.cs.washington.edu/projects/timelapse3d/

[3]https://grail.cs.washington.edu/rome/

[4]http://www.theverge.com/2015/9/29/9413583/apple-maps-3d-flyo...

toomuchtodo4• 10 years ago

You'll want to use the OpenStreetView dataset for that, which has a much more liberal license for collected images than Mapillary. (OSV is a direct competitor to Mapillary, with OSV being sponsored by Navteq)

http://openstreetview.com/terms/

You might also consider mining Flickr by geotag, constraining to CC licenses that allow for use.

maxerickson4• 10 years ago

Or even just directly capture geotagged photos. That's going to be the best way to ensure good coverage of the target area.

ris• 10 years ago

OSV is a direct competitor to Mapillary, with OSV being sponsored by Navteq

s/Navteq/Telenav/

MichailP3• 10 years ago

Thanks for the very informative and detailed answers. The Google TOS seems very restrictive, and I can't quite stomach the idea that our data, including photo of my house, is free to use by big companies in any way conceivable, but on the other hand, a small, maybe scientific purpose, is in violation of TOS :(

abstractbeliefs• 10 years ago

Photos of a house from the public street isn't your data though. This is why you are empowered to go and collect all sorts of data and information that is exposed to the public in all sorts of ways, and do with it as you please.

You have just as much right to take pictures of Google's complexes from public locations and bill them should they want to use what you have collected, and this whole situation is really a good thing. Things in the public domain are in the public domain.

data0815• 10 years ago

How well would this work in a situation with artificial (moving) lighting? I have seen reconstructions for wrecks underwater, and we are interested in doing something similar.

rasmi2• 10 years ago

It is possible to correct for all sorts of different lighting conditions. See here: http://grail.cs.washington.edu/projects/timelapse/

jsch• 10 years ago

COLMAP is an open source structure-from-motion and multi-view stereo software and is hopefully useful for people here as well: https://colmap.github.io/, http://people.inf.ethz.ch/jschoenb/colmap/

BHSPitMonkey• 10 years ago

What techniques are available to transform point clouds like these into closed polygonal meshes (like the ones you see in Google Earth where 3D imagery is available)?

zump• 10 years ago

So why can't this be used instead of LIDAR for Self-Driving cars?

Experts?

Denser 3D Point Clouds in OpenSfM

Related Stories