Monocular Depth Estimation with Global-Aware Discretization and Local Context Modeling

TL;DR

This paper introduces a novel monocular depth estimation approach that combines local and global cues using specialized modules, significantly improving accuracy and outperforming existing methods on standard datasets.

Contribution

The paper proposes the Gated Large Kernel Attention Module and Global Bin Prediction Module to enhance local and global feature extraction for monocular depth estimation.

Findings

Achieves state-of-the-art performance on NYU-V2 and KITTI datasets.

Effectively captures multi-scale local structural information.

Provides structural guidance through global depth distribution estimation.

Abstract

Accurate monocular depth estimation remains a challenging problem due to the inherent ambiguity that stems from the ill-posed nature of recovering 3D structure from a single view, where multiple plausible depth configurations can produce identical 2D projections. In this paper, we present a novel depth estimation method that combines both local and global cues to improve prediction accuracy. Specifically, we propose the Gated Large Kernel Attention Module (GLKAM) to effectively capture multi-scale local structural information by leveraging large kernel convolutions with a gated mechanism. To further enhance the global perception of the network, we introduce the Global Bin Prediction Module (GBPM), which estimates the global distribution of depth bins and provides structural guidance for depth regression. Extensive experiments on the NYU-V2 and KITTI dataset demonstrate that our method achieves competitive performance and outperforms existing approaches, validating the effectiveness of each proposed component.