Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark

TL;DR

This paper introduces a novel self-supervised monocular depth estimation framework that effectively handles nighttime challenges by incorporating priors, image enhancement, and dynamic masking, achieving state-of-the-art results.

Contribution

It proposes a comprehensive framework with priors-based regularization, image enhancement, and a statistics-based masking strategy specifically designed for nighttime depth estimation.

Findings

Achieves state-of-the-art performance on nighttime datasets.

Improves depth accuracy in low-visibility and varying illumination conditions.

Demonstrates effectiveness of each proposed component through experiments.

Abstract

Monocular depth estimation aims at predicting depth from a single image or video. Recently, self-supervised methods draw much attention since they are free of depth annotations and achieve impressive performance on several daytime benchmarks. However, they produce weird outputs in more challenging nighttime scenarios because of low visibility and varying illuminations, which bring weak textures and break brightness-consistency assumption, respectively. To address these problems, in this paper we propose a novel framework with several improvements: (1) we introduce Priors-Based Regularization to learn distribution knowledge from unpaired depth maps and prevent model from being incorrectly trained; (2) we leverage Mapping-Consistent Image Enhancement module to enhance image visibility and contrast while maintaining brightness consistency; and (3) we present Statistics-Based Mask strategy to tune the number of removed pixels within textureless regions, using dynamic statistics. Experimental results demonstrate the effectiveness of each component. Meanwhile, our framework achieves remarkable improvements and state-of-the-art results on two nighttime datasets.