BVI-Lowlight: Fully Registered Benchmark Dataset for Low-Light Video Enhancement
This provides a benchmark dataset for researchers in computer vision working on low-light video enhancement, addressing a data scarcity issue, but it is incremental as it focuses on dataset creation rather than new methods.
The paper tackles the scarcity of training data for low-light video enhancement by introducing a novel dataset of 40 scenes with fully registered ground truth, captured under two low-light conditions with genuine noise and temporal artifacts, and demonstrates its significance through experimental results.
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.