MetricDepth: Enhancing Monocular Depth Estimation with Deep Metric Learning

TL;DR

MetricDepth introduces a novel deep metric learning approach with differential-based sample identification and multi-range negative sample strategy to significantly improve monocular depth estimation accuracy across diverse datasets.

Contribution

This paper presents a new method, MetricDepth, that adapts deep metric learning for monocular depth estimation by designing differential-based sample identification and a multi-range negative sample strategy.

Findings

Enhanced depth estimation accuracy across multiple datasets.

Effective feature regularization through differential-based sample identification.

Versatile performance across various model architectures.

Abstract

Deep metric learning aims to learn features relying on the consistency or divergence of class labels. However, in monocular depth estimation, the absence of a natural definition of class poses challenges in the leveraging of deep metric learning. Addressing this gap, this paper introduces MetricDepth, a novel method that integrates deep metric learning to enhance the performance of monocular depth estimation. To overcome the inapplicability of the class-based sample identification in previous deep metric learning methods to monocular depth estimation task, we design the differential-based sample identification. This innovative approach identifies feature samples as different sample types by their depth differentials relative to anchor, laying a foundation for feature regularizing in monocular depth estimation models. Building upon this advancement, we then address another critical problem caused by the vast range and the continuity of depth annotations in monocular depth estimation. The extensive and continuous annotations lead to the diverse differentials of negative samples to anchor feature, representing the varied impact of negative samples during feature regularizing. Recognizing the inadequacy of the uniform strategy in previous deep metric learning methods for handling negative samples in monocular depth estimation task, we propose the multi-range strategy. Through further distinction on negative samples according to depth differential ranges and implementation of diverse regularizing, our multi-range strategy facilitates differentiated regularization interactions between anchor feature and its negative samples. Experiments across various datasets and model types demonstrate the effectiveness and versatility of MetricDepth,confirming its potential for performance enhancement in monocular depth estimation task.