Semi-dense visual odometry for AR on a smartphone

Thomas Schops, Jakob Engel, Daniel Cremers
2014 2014 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)  
Figure 1 : From left to right: AR demo application with simulated car. Corresponding estimated semi-dense depth map. Estimated dense collision mesh, fixed and shown from a different perspective. Photo of running system. The attached video shows the system in action. ABSTRACT We present a direct monocular visual odometry system which runs in real-time on a smartphone. Being a direct method, it tracks and maps on the images themselves instead of extracted features such as keypoints. New images
more » ... tracked using direct image alignment, while geometry is represented in the form of a semi-dense depth map. Depth is estimated by filtering over many small-baseline, pixel-wise stereo comparisons. This leads to significantly less outliers and allows to map and use all image regions with sufficient gradient, including edges. We show how a simple world model for AR applications can be derived from semi-dense depth maps, and demonstrate the practical applicability in the context of an AR application in which simulated objects can collide with real geometry.
doi:10.1109/ismar.2014.6948420 dblp:conf/ismar/SchopsEC14 fatcat:55wtg7fpvvfzrm76djxoy53lvq