On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression
This work addresses the problem of improving depth accuracy and uncertainty quantification for tasks like autonomous driving, but it is incremental as it builds on existing CAR methods.
The paper tackles the lack of detailed descriptions and comparisons for Classification Approaches for Regression (CAR) in monocular depth estimation, introducing a taxonomy, a new uncertainty estimation method, and experiments on the KITTI dataset, where the new method outperforms ensembling with only one forward propagation.
Monocular depth is important in many tasks, such as 3D reconstruction and autonomous driving. Deep learning based models achieve state-of-the-art performance in this field. A set of novel approaches for estimating monocular depth consists of transforming the regression task into a classification one. However, there is a lack of detailed descriptions and comparisons for Classification Approaches for Regression (CAR) in the community and no in-depth exploration of their potential for uncertainty estimation. To this end, this paper will introduce a taxonomy and summary of CAR approaches, a new uncertainty estimation solution for CAR, and a set of experiments on depth accuracy and uncertainty quantification for CAR-based models on KITTI dataset. The experiments reflect the differences in the portability of various CAR methods on two backbones. Meanwhile, the newly proposed method for uncertainty estimation can outperform the ensembling method with only one forward propagation.