LLVIP

A Visible-infrared Paired Dataset for Low-light Vision

Dataset Information
Modalities
Images
Languages
English, Chinese
Introduced
2021
License
This LLVIP Dataset is made freely available to academic and non-academic entities for non-commercial purposes such as academic research, teaching, scientific publications, or personal experimentation. Permission is granted to use the data given that you agree to our license terms.
Homepage
Official Website
Contents

Overview

  • Visible-infrared Paired Dataset for Low-light Vision
  • 30976 images (15488 pairs)
  • 24 dark scenes, 2 daytime scenes
  • Support for image-to-image translation (visible to infrared, or infrared to visible), visible and infrared image fusion, low-light pedestrian detection, and infrared pedestrian detection
  • (The original image and video pairs (before registration) of LLVIP are also released!)

Variants: LLVIP

Associated Benchmarks

This dataset is used in 5 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Pedestrian Detection MMPedestron When Pedestrian Detection Meets Multi-Modal … 2024-07-14
Object Detection MiPa MiPa: Mixed Patch Infrared-Visible Modality … 2024-04-29
Pedestrian Detection MiPa MiPa: Mixed Patch Infrared-Visible Modality … 2024-04-29
Pedestrian Detection UniRGB-IR UniRGB-IR: A Unified Framework for … 2024-04-26
Pedestrian Detection RSDet Removal then Selection: A Coarse-to-Fine … 2024-01-19
Image-to-Image Translation cycleGAN BCI: Breast Cancer Immunohistochemical Image … 2022-04-25
Image-to-Image Translation pix2pixHD BCI: Breast Cancer Immunohistochemical Image … 2022-04-25
Image-to-Image Translation pyramidpix2pix BCI: Breast Cancer Immunohistochemical Image … 2022-04-25
Pedestrian Detection CMX CMX: Cross-Modal Fusion for RGB-X … 2022-03-09
Multispectral Object Detection CFT Cross-Modality Fusion Transformer for Multispectral … 2021-10-30
Pedestrian Detection CFT Cross-Modality Fusion Transformer for Multispectral … 2021-10-30
Image Generation pix2pix LLVIP: A Visible-infrared Paired Dataset … 2021-08-24
Pedestrian Detection YoloV5-RGB LLVIP: A Visible-infrared Paired Dataset … 2021-08-24
Pedestrian Detection YoloV3-RGB LLVIP: A Visible-infrared Paired Dataset … 2021-08-24
Image-to-Image Translation pix2pix LLVIP: A Visible-infrared Paired Dataset … 2021-08-24
Pedestrian Detection ProbEn Multimodal Object Detection via Probabilistic … 2021-04-07

Research Papers

Recent papers with results on this dataset:

External Links: