Depth Map Decomposition for Monocular Depth Estimation

TL;DR

This paper introduces a depth map decomposition method for monocular depth estimation that leverages shared encoders and multiple decoders to improve accuracy, especially with limited metric depth data.

Contribution

It presents a novel network architecture that decomposes depth maps and utilizes datasets without metric labels to enhance estimation performance.

Findings

Competitive performance against state-of-the-art methods

Effective with limited metric depth training data

Improves metric depth estimation accuracy

Abstract

We propose a novel algorithm for monocular depth estimation that decomposes a metric depth map into a normalized depth map and scale features. The proposed network is composed of a shared encoder and three decoders, called G-Net, N-Net, and M-Net, which estimate gradient maps, a normalized depth map, and a metric depth map, respectively. M-Net learns to estimate metric depths more accurately using relative depth features extracted by G-Net and N-Net. The proposed algorithm has the advantage that it can use datasets without metric depth labels to improve the performance of metric depth estimation. Experimental results on various datasets demonstrate that the proposed algorithm not only provides competitive performance to state-of-the-art algorithms but also yields acceptable results even when only a small amount of metric depth data is available for its training.