Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks

TL;DR

This paper presents a novel approach to monocular depth estimation by formulating it as a pixel-wise classification task using deep residual networks, achieving state-of-the-art results on indoor and outdoor datasets.

Contribution

The authors introduce a classification-based method for depth estimation with deep residual networks and incorporate CRF for improved local smoothness, advancing the accuracy of monocular depth prediction.

Findings

Achieved state-of-the-art performance on benchmark datasets.

Discretizing depth improves confidence estimation.

CRF post-processing enhances local consistency.

Abstract

Depth estimation from single monocular images is a key component of scene understanding and has benefited largely from deep convolutional neural networks (CNN) recently. In this article, we take advantage of the recent deep residual networks and propose a simple yet effective approach to this problem. We formulate depth estimation as a pixel-wise classification task. Specifically, we first discretize the continuous depth values into multiple bins and label the bins according to their depth range. Then we train fully convolutional deep residual networks to predict the depth label of each pixel. Performing discrete depth label classification instead of continuous depth value regression allows us to predict a confidence in the form of probability distribution. We further apply fully-connected conditional random fields (CRF) as a post processing step to enforce local smoothness interactions, which improves the results. We evaluate our approach on both indoor and outdoor datasets and achieve state-of-the-art performance.