LLVIP: A Visible-infrared Paired Dataset for Low-light Vision

TL;DR

LLVIP is a large, aligned visible-infrared dataset designed for low-light vision tasks, enabling improved research in image fusion, pedestrian detection, and image translation under very dark conditions.

Contribution

The paper introduces LLVIP, a new extensive paired dataset for low-light vision, with aligned images and pedestrian labels, facilitating research in challenging dark environments.

Findings

Fusion enhances image information in low-light scenes.

Existing algorithms underperform in very low-light conditions.

LLVIP dataset promotes advancements in low-light vision tasks.

Abstract

It is very challenging for various visual tasks such as image fusion, pedestrian detection and image-to-image translation in low light conditions due to the loss of effective target areas. In this case, infrared and visible images can be used together to provide both rich detail information and effective target areas. In this paper, we present LLVIP, a visible-infrared paired dataset for low-light vision. This dataset contains 30976 images, or 15488 pairs, most of which were taken at very dark scenes, and all of the images are strictly aligned in time and space. Pedestrians in the dataset are labeled. We compare the dataset with other visible-infrared datasets and evaluate the performance of some popular visual algorithms including image fusion, pedestrian detection and image-to-image translation on the dataset. The experimental results demonstrate the complementary effect of fusion on image information, and find the deficiency of existing algorithms of the three visual tasks in very low-light conditions. We believe the LLVIP dataset will contribute to the community of computer vision by promoting image fusion, pedestrian detection and image-to-image translation in very low-light applications. The dataset is being released in https://bupt-ai-cz.github.io/LLVIP. Raw data is also provided for further research such as image registration.