Now showing items 1-2 of 2
Encoding 3D contextual information for dynamic scene understanding
(Georgia Institute of Technology, 2020-04-27)
This thesis aims to demonstrate how using 3D cues improves semantic labeling and object classification. Specifically, we will consider depth, surface normals, object classification, and pixel-wise semantic labeling in this ...
Robust approaches and optimization for 3D data
(Georgia Institute of Technology, 2018-04-06)
We introduce a robust, purely geometric, representation framework for fundamental association and analysis problems involving multiple views and scenes. The framework utilizes surface patches / segments as the underlying ...