Denser 3D Point Clouds in OpenSfM

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

Re: Denser 3D Point Clouds in OpenSfM

#8

Post by deckar01 » Mon, Oct 31, 2016, 2:06 PM UTC

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.

Re: Denser 3D Point Clouds in OpenSfM

#9

Post by yubin » Mon, Oct 31, 2016, 2:15 PM UTC

yummybear wrote: post #3

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?

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.

Re: Denser 3D Point Clouds in OpenSfM

#10

Post by yubin » Mon, Oct 31, 2016, 2:18 PM UTC

dharma1 wrote: post #7

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

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.