Documentation: https://mmflow.readthedocs.io/
English | 简体中文
MMFlow is an open source optical flow toolbox based on PyTorch. It is a part of the OpenMMLab project.
The master branch works with PyTorch 1.5+.
mmflow_readme.mp4
-
The First Unified Framework for Optical Flow
MMFlow is the first toolbox that provides a framework for unified implementation and evaluation of optical flow methods.
-
Flexible and Modular Design
We decompose the flow estimation framework into different components and one can build a new model easily and flexibly by combining different modules.
-
Plenty of Algorithms and Datasets Out of the Box
The toolbox directly supports popular and contemporary optical flow methods, e.g. FlowNet, PWC-Net, RAFT, etc, and representative datasets, FlyingChairs, FlyingThings3D, Sintel, KITTI, etc.
This project is released under the Apache 2.0 license.
Results and models are available in the model zoo.
Supported methods:
- FlowNet (ICCV'2015)
- FlowNet2 (CVPR'2017)
- PWC-Net (CVPR'2018)
- LiteFlowNet (CVPR'2018)
- LiteFlowNet2 (TPAMI'2020)
- IRR (CVPR'2019)
- MaskFlownet (CVPR'2020)
- RAFT (ECCV'2020)
Please refer to install.md for installation and guidance in dataset_prepare for dataset preparation.
If you're new of optical flow, you can start with Learn the basics. If you’re familiar with it, check out getting_started.md to try out MMFlow.
Refer to the below tutorials to dive deeper:
We appreciate all contributions improving MMFlow. Please refer to CONTRIBUTING.md in MMCV for more details about the contributing guideline.
If you use this toolbox or benchmark in your research, please cite this project.
@misc{2021mmflow,
title={{MMFlow}: OpenMMLab Optical Flow Toolbox and Benchmark},
author={MMFlow Contributors},
howpublished = {\url{https://github.com/open-mmlab/mmflow}},
year={2021}
}
- MMCV: OpenMMLab foundational library for computer vision.
- MIM: MIM Installs OpenMMLab Packages.
- MMClassification: OpenMMLab image classification toolbox and benchmark.
- MMDetection: OpenMMLab detection toolbox and benchmark.
- MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
- MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
- MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
- MMTracking: OpenMMLab video perception toolbox and benchmark.
- MMPose: OpenMMLab pose estimation toolbox and benchmark.
- MMEditing: OpenMMLab image and video editing toolbox.
- MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding.
- MMGeneration: OpenMMLab image and video generative models toolbox.
- MMFlow: OpenMMLab optical flow toolbox and benchmark.