English | 简体中文
LQIT is an open source Low-Quality Image Toolbox, including low-quality (underwater, foggy, low-light, etc.) image enhancement tasks, and related high-level computer vision tasks (such as object detection). LQIT depends on PyTorch and OpenMMLab 2.0 series.
The main branch works with PyTorch 1.6+. The compatibility to earlier versions of PyTorch is not fully tested.
v0.0.1rc2 was released in 28/10/2023:
- Support FeiShu (Lark) robot
- Support TIENet, UOD-AIR, and RDFFNet
- Release
RTTSfoggy object detection models
Please refer to changelog for details and release history.
LQIT depends on PyTorch, MMEngine, MMCV, and MMEval. It also can use OpenMMLab codebases as a dependency, such as MMDetection.
Please refer to Installation for installation of LQIT and data preparation for dataset preparation.
We appreciate all contributions to improve LQIT. Please refer to CONTRIBUTING.md for the contributing guideline.
LQIT is released under the Apache 2.0 license, while some specific features in this library are with other licenses. Please refer to LICENSES.md for the careful check, if you are using our code for commercial matters.
If you have any questions, please contact Yudong Wang at yudongwang1226@gmail.com or yudongwang@tju.edu.cn.