DepthDark: Robust Monocular Depth Estimation for Low-Light Environments

TL;DR

DepthDark introduces a robust foundation model for monocular depth estimation in low-light environments, leveraging novel simulation modules and a specialized fine-tuning strategy to outperform existing methods on challenging datasets.

Contribution

The paper presents a new low-light simulation framework and a parameter-efficient fine-tuning approach, enabling effective depth estimation in nighttime conditions with limited data.

Findings

Achieves state-of-the-art performance on nuScenes-Night and RobotCar-Night datasets.

Effectively utilizes limited training data and computational resources.

Enhances depth estimation accuracy in low-light environments.

Abstract

In recent years, foundation models for monocular depth estimation have received increasing attention. Current methods mainly address typical daylight conditions, but their effectiveness notably decreases in low-light environments. There is a lack of robust foundational models for monocular depth estimation specifically designed for low-light scenarios. This largely stems from the absence of large-scale, high-quality paired depth datasets for low-light conditions and the effective parameter-efficient fine-tuning (PEFT) strategy. To address these challenges, we propose DepthDark, a robust foundation model for low-light monocular depth estimation. We first introduce a flare-simulation module and a noise-simulation module to accurately simulate the imaging process under nighttime conditions, producing high-quality paired depth datasets for low-light conditions. Additionally, we present an effective low-light PEFT strategy that utilizes illumination guidance and multiscale feature fusion to enhance the model's capability in low-light environments. Our method achieves state-of-the-art depth estimation performance on the challenging nuScenes-Night and RobotCar-Night datasets, validating its effectiveness using limited training data and computing resources.