NOTICE: SMARTech content freeze Dec. 10 - 17. The Library will be unable to deposit or edit content during this scheduled maintenance
Now showing items 1-1 of 1
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 ...