On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression

TL;DR

This paper explores classification-based approaches for monocular depth estimation, introduces a taxonomy, and proposes a new uncertainty estimation method that outperforms ensembling with less computation.

Contribution

It provides a comprehensive taxonomy of CAR methods, introduces a novel uncertainty estimation technique, and evaluates their performance on the KITTI dataset.

Findings

CAR methods vary in depth accuracy and portability across backbones.

The proposed uncertainty estimation outperforms ensembling with a single forward pass.

CAR approaches are effective for monocular depth and uncertainty estimation.

Abstract

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.