A Weakly-Supervised Depth Estimation Network Using Attention Mechanism

TL;DR

This paper introduces a weakly-supervised depth estimation network using attention mechanisms that effectively handles incorrect labels, improving performance on monocular depth estimation tasks.

Contribution

The paper proposes a novel attention nested U-net framework with soft label generation for weakly-supervised monocular depth estimation, addressing label inaccuracies.

Findings

Outperforms state-of-the-art methods on public datasets

Effective handling of false labels with soft label generation

Demonstrates robustness on defective monocular depth datasets

Abstract

Monocular depth estimation (MDE) is a fundamental task in many applications such as scene understanding and reconstruction. However, most of the existing methods rely on accurately labeled datasets. A weakly-supervised framework based on attention nested U-net (ANU) named as ANUW is introduced in this paper for cases with wrong labels. The ANUW is trained end-to-end to convert an input single RGB image into a depth image. It consists of a dense residual network structure, an adaptive weight channel attention (AWCA) module, a patch second non-local (PSNL) module and a soft label generation method. The dense residual network is the main body of the network to encode and decode the input. The AWCA module can adaptively adjust the channel weights to extract important features. The PSNL module implements the spatial attention mechanism through a second-order non-local method. The proposed soft label generation method uses the prior knowledge of the dataset to produce soft labels to replace false ones. The proposed ANUW is trained on a defective monocular depth dataset and the trained model is tested on three public datasets, and the results demonstrate the superiority of ANUW in comparison with the state-of-the-art MDE methods.