Deep Classification Network for Monocular Depth Estimation
This work addresses depth estimation for computer vision applications, but it is incremental as it adapts an existing segmentation method to a related task.
The authors tackled monocular depth estimation by reframing it as a pixel-level classification problem, using depth increments and Deeplab v2 to achieve a state-of-the-art result on the KITTI dataset with an 8% improvement over existing methods.
Monocular Depth Estimation is usually treated as a supervised and regression problem when it actually is very similar to semantic segmentation task since they both are fundamentally pixel-level classification tasks. We applied depth increments that increases with depth in discretizing depth values and then applied Deeplab v2 and the result was higher accuracy. We were able to achieve a state-of-the-art result on the KITTI dataset and outperformed existing architecture by an 8% margin.