ucla-vision / xivo

X Inertial-aided Visual Odometry
Other
851 stars 120 forks source link

Triangulate using more than two frames #74

Open stephanietsuei opened 1 year ago

stephanietsuei commented 1 year ago

We currently find an initial depth estimate of features using a combination of a subfilter and triangulation. XIVO triangulates after only two frames, even though there is often not much parallax after only two frames.