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

08/24/2021
by   Xinyu Jia, et al.
9

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 33672 images, or 16836 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.

READ FULL TEXT

page 1

page 2

page 3

page 5

page 7

page 8

research
09/08/2022

Application of image-to-image translation in improving pedestrian detection

The lack of effective target regions makes it difficult to perform sever...
research
03/17/2023

Pedestrain detection for low-light vision proposal

The demand for pedestrian detection has created a challenging problem fo...
research
07/06/2022

Local Relighting of Real Scenes

We introduce the task of local relighting, which changes a photograph of...
research
05/26/2023

TFDet: Target-aware Fusion for RGB-T Pedestrian Detection

Pedestrian detection is a critical task in computer vision because of it...
research
09/15/2016

Visible Light-Based Human Visual System Conceptual Model

There is a widely held belief in the digital image and video processing ...
research
05/09/2022

Paired Image-to-Image Translation Quality Assessment Using Multi-Method Fusion

How best to evaluate synthesized images has been a longstanding problem ...
research
10/13/2022

What's in a Decade? Transforming Faces Through Time

How can one visually characterize people in a decade? In this work, we a...

Please sign up or login with your details

Forgot password? Click here to reset