Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions

TL;DR

This paper presents a neural network approach for monocular depth estimation that predicts local geometric cues as probability distributions, and then harmonizes these predictions to produce a consistent depth map, improving accuracy on NYU v2 data.

Contribution

The method introduces overcomplete local predictions of depth derivatives with confidence measures, combined through a globalization process for improved depth estimation.

Findings

Effective depth estimation on NYU v2 dataset

Probabilistic local derivative predictions enhance accuracy

Global harmonization yields consistent depth maps

Abstract

A single color image can contain many cues informative towards different aspects of local geometric structure. We approach the problem of monocular depth estimation by using a neural network to produce a mid-level representation that summarizes these cues. This network is trained to characterize local scene geometry by predicting, at every image location, depth derivatives of different orders, orientations and scales. However, instead of a single estimate for each derivative, the network outputs probability distributions that allow it to express confidence about some coefficients, and ambiguity about others. Scene depth is then estimated by harmonizing this overcomplete set of network predictions, using a globalization procedure that finds a single consistent depth map that best matches all the local derivative distributions. We demonstrate the efficacy of this approach through evaluation on the NYU v2 depth data set.