News for hackers. Stuff that matters.

A comment on Forge – mobile 3-D capture [video]. Parent comment

Re:Forge – mobile 3-D capture [video] by nobbis on Wednesday March 26, 2014 @01:20PM (#7474837)
Author here. It uses color info as well as depth for tracking. Otherwise, it'd fail if you pointed the camera at featureless geometry, e.g. walls, floors.
[ Parent | on HN ]
Re:Forge – mobile 3-D capture [video] by phorese on Wednesday March 26, 2014 @01:23PM (#7474870)
Looks great :)

In the video it looks like you are using a volumetric representation, perhaps an Octree+isosurface extraction?

[ Parent | on HN ]
Re:Forge – mobile 3-D capture [video] by nobbis on Wednesday March 26, 2014 @01:34PM (#7474931)
Correct. It stores a volumetric signed distance function in a tree-structure, which makes mesh generation (and raytracing) simple and fast.
[ Parent | on HN ]
Re:Forge – mobile 3-D capture [video] by druidsbane on Wednesday March 26, 2014 @03:19PM (#7475759)
Can it stitch together much larger captures? eg: a building exterior and interior?
[ Parent | on HN ]
Re:Forge – mobile 3-D capture [video] by nobbis on Wednesday March 26, 2014 @05:12PM (#7476709)
You can download and manually align separate captures to create a larger mesh but, no, Forge doesn't do this automatically yet.

On the roadmap, but won't be in the first version.

[ Parent | on HN ]
Re:Forge – mobile 3-D capture [video] by joshvm on Wednesday March 26, 2014 @05:02PM (#7476631)
Looks neat - what depth sensor were you using to generate that video? It's not totally clear to me from the comments.
[ Parent | on HN ]