LMDepth: Lightweight Mamba-based Monocular Depth Estimation for Real-World Deployment

TL;DR

LMDepth is a lightweight, efficient monocular depth estimation network that balances high accuracy with low computational cost, suitable for deployment on resource-constrained devices.

Contribution

The paper introduces LMDepth, a novel Mamba-based architecture with a pyramid spatial pooling module and depth Mamba blocks, offering a lightweight alternative to Transformer-based methods.

Findings

Outperforms previous lightweight methods on NYUDv2 and KITTI datasets.

Achieves higher accuracy with fewer parameters and GFLOPs.

Successfully deployed on embedded platform with INT8 quantization.

Abstract

Monocular depth estimation provides an additional depth dimension to RGB images, making it widely applicable in various fields such as virtual reality, autonomous driving and robotic navigation. However, existing depth estimation algorithms often struggle to effectively balance performance and computational efficiency, which poses challenges for deployment on resource-constrained devices. To address this, we propose LMDepth, a lightweight Mamba-based monocular depth estimation network, designed to reconstruct high-precision depth information while maintaining low computational overhead. Specifically, we propose a modified pyramid spatial pooling module that serves as a multi-scale feature aggregator and context extractor, ensuring global spatial information for accurate depth estimation. Moreover, we integrate multiple depth Mamba blocks into the decoder. Designed with linear computations, the Mamba Blocks enable LMDepth to efficiently decode depth information from global features, providing a lightweight alternative to Transformer-based architectures that depend on complex attention mechanisms. Extensive experiments on the NYUDv2 and KITTI datasets demonstrate the effectiveness of our proposed LMDepth. Compared to previous lightweight depth estimation methods, LMDepth achieves higher performance with fewer parameters and lower computational complexity (measured by GFLOPs). We further deploy LMDepth on an embedded platform with INT8 quantization, validating its practicality for real-world edge applications.