ralph0813 / openstereo Goto Github PK

OpenStereo is a flexible and extensible stereo matching project.

• [March 2023]:OpenStereo is available!!!

• Mutiple Dataset supported: OpenStereo supports six popular stereo datasets: SceneFlow, KITTI12 & KITTI15, ETH3D and DrivingStereo .
• Multiple Models Support: We reproduced several SOTA methods, and reached the same or even the better performance.
• DDP Support: The officially recommended Distributed Data Parallel (DDP) mode is used during both the training and testing phases.
• AMP Support: The Auto Mixed Precision (AMP) option is available.
• Nice log: We use tensorboard and logging to log everything, which looks pretty.

Please see 0.get_started.md. We also provide the following tutorials for your reference:

• Prepare dataset
• Detailed configuration
• Customize model
• Advanced usages

Results and models are available in the model zoo.

OpenStereo Team (OST)

• Xianda Guo (国显达), [email protected]
• Juntao Lu (陆俊陶), [email protected]
• Yiqi Wang (王仪琦), [email protected]
• Yiqun Duan (段逸群), [email protected]
• Zheng Zhu (朱政),[email protected]

• AANet
• ACVNet
• CascadeStereo
• CFNet
• COEX
• DenseMatching
• FADNet
• GANet
• GwcNet
• LacGwcNet
• MSNet
• PSMNet
• RAFT
• STTR
• OpenGait