BVI-Lowlight: Fully Registered Benchmark Dataset for Low-Light Video Enhancement

TL;DR

This paper introduces a fully registered low-light video dataset with ground truth in normal lighting, enabling better training and evaluation of enhancement algorithms for low-light videos.

Contribution

The creation of a novel, fully registered low-light video dataset with ground truth data, addressing the scarcity of training data for low-light video enhancement.

Findings

Fully registered video pairs improve enhancement methods.

The dataset is extensive and representative for supervised learning.

Experimental results highlight the importance of registration in low-light video enhancement.

Abstract

Low-light videos often exhibit spatiotemporal incoherent noise, leading to poor visibility and compromised performance across various computer vision applications. One significant challenge in enhancing such content using modern technologies is the scarcity of training data. This paper introduces a novel low-light video dataset, consisting of 40 scenes captured in various motion scenarios under two distinct low-lighting conditions, incorporating genuine noise and temporal artifacts. We provide fully registered ground truth data captured in normal light using a programmable motorized dolly, and subsequently, refine them via image-based post-processing to ensure the pixel-wise alignment of frames in different light levels. This paper also presents an exhaustive analysis of the low-light dataset, and demonstrates the extensive and representative nature of our dataset in the context of supervised learning. Our experimental results demonstrate the significance of fully registered video pairs in the development of low-light video enhancement methods and the need for comprehensive evaluation. Our dataset is available at DOI:10.21227/mzny-8c77.