LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond

TL;DR

This paper introduces LoLI-Street, a new street scene low-light image dataset, and proposes TriFuse, a transformer and diffusion-based model, to improve low-light image enhancement for autonomous driving and surveillance.

Contribution

The paper provides a large, annotated street scene dataset for low-light enhancement and introduces TriFuse, a novel transformer and diffusion-based model, to advance LLIE performance in real-world conditions.

Findings

TriFuse outperforms existing models on LoLI-Street

Enhanced object detection in low-light conditions

Improved generalization across multiple datasets

Abstract

Low-light image enhancement (LLIE) is essential for numerous computer vision tasks, including object detection, tracking, segmentation, and scene understanding. Despite substantial research on improving low-quality images captured in underexposed conditions, clear vision remains critical for autonomous vehicles, which often struggle with low-light scenarios, signifying the need for continuous research. However, paired datasets for LLIE are scarce, particularly for street scenes, limiting the development of robust LLIE methods. Despite using advanced transformers and/or diffusion-based models, current LLIE methods struggle in real-world low-light conditions and lack training on street-scene datasets, limiting their effectiveness for autonomous vehicles. To bridge these gaps, we introduce a new dataset LoLI-Street (Low-Light Images of Streets) with 33k paired low-light and well-exposed images from street scenes in developed cities, covering 19k object classes for object detection. LoLI-Street dataset also features 1,000 real low-light test images for testing LLIE models under real-life conditions. Furthermore, we propose a transformer and diffusion-based LLIE model named "TriFuse". Leveraging the LoLI-Street dataset, we train and evaluate our TriFuse and SOTA models to benchmark on our dataset. Comparing various models, our dataset's generalization feasibility is evident in testing across different mainstream datasets by significantly enhancing images and object detection for practical applications in autonomous driving and surveillance systems. The complete code and dataset is available on https://github.com/tanvirnwu/TriFuse.