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

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

24 Aug 2021arXiv:2108.10831archive 2025-07-28

Xinyu Jia, Chuang Zhu, Minzhen Li, Wenqi Tang, ShengJie Liu, Wenli Zhou

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.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

bupt-ai-cz/LLVIP officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image GenerationImage RegistrationImage-to-Image TranslationInfrared And Visible Image FusionLow-Light Image EnhancementLow-light Pedestrian DetectionMultispectral Object DetectionPedestrian DetectionThermal Infrared Pedestrian DetectionTranslation

Datasets

Introduced by this paper, per the archive.

LLVIP

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation LLVIP pix2pix PSNR 10.769 #1 of 1 Archive leaderboard report
Image Generation LLVIP pix2pix SSIM 0.1757 #1 of 1 Archive leaderboard report
Image-to-Image Translation LLVIP pix2pix PSNR 10.769 #4 of 4 Archive leaderboard report
Image-to-Image Translation LLVIP pix2pix SSIM 0.1757 #4 of 4 Archive leaderboard report
Pedestrian Detection LLVIP YoloV5-RGB AP 0.527 #11 of 15 Archive leaderboard report
Pedestrian Detection LLVIP YoloV5-RGB log average miss rate 22.59% #11 of 15 Archive leaderboard report
Pedestrian Detection LLVIP YoloV3-RGB AP 0.466 #14 of 15 Archive leaderboard report
Pedestrian Detection LLVIP YoloV3-RGB log average miss rate 37.70% #14 of 15 Archive leaderboard report
Thermal Infrared Pedestrian Detection LLVIP YoloV5 AP 0.670 #1 of 2 Archive leaderboard report
Thermal Infrared Pedestrian Detection LLVIP YoloV3 AP 0.582 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Batch NormalizationConcatenated Skip ConnectionConvolutionDropoutPatchGANPix2PixReLUSigmoid Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections