文件名称：PSMNet代码
文件大小：46KB
文件格式：ZIP
更新时间：2022-05-03 07:35:16
code stereo
Pyramid Stereo Matching Network (PSMNet)的代码。 Recent work has shown that depth estimation from a stereo pair of images can be formulated as a supervised learning task to be resolved with convolutional neural networks (CNNs). However, current architectures rely on patch-based Siamese networks, lacking the means to exploit context information for finding correspondence in illposed regions. To tackle this problem, we propose PSMNet, a pyramid stereo matching network consisting of two main modules: spatial pyramid pooling and 3D CNN. The spatial pyramid pooling module takes advantage of the capacity of global context information by aggregating context in different scales and locations to form a cost volume. The3DCNNlearnstoregularizecostvolumeusingstacked multiple hourglass networks in conjunction with intermediate supervision. The proposed approach was evaluated on several benchmark datasets. Our method ranked first in the KITTI 2012 and 2015 leaderboards before March 18, 2018.
【文件预览】：
PSMNet-master
----utils()
--------readpfm.pyc(1KB)
--------__init__.pyc(134B)
--------__init__.py(0B)
--------preprocess.pyc(7KB)
--------preprocess.py(5KB)
--------readpfm.py(914B)
----models()
--------__init__.pyc(224B)
--------submodule.pyc(7KB)
--------__init__.py(89B)
--------basic.py(4KB)
--------stackhourglass.pyc(5KB)
--------stackhourglass.py(6KB)
--------submodule.py(6KB)
--------basic.pyc(3KB)
----submission.py(4KB)
----main.py(6KB)
----run.sh(572B)
----dataset()
--------Readme.md(846B)
----finetune.py(7KB)
----LICENSE(1KB)
----dataloader()
--------readpfm.pyc(1KB)
--------KITTIloader2015.pyc(2KB)
--------KITTIloader2015.py(1KB)
--------__init__.pyc(139B)
--------KITTILoader.py(2KB)
--------KITTI_submission_loader.py(632B)
--------listflowfile.pyc(4KB)
--------KITTI_submission_loader.pyc(1KB)
--------__init__.py(0B)
--------SecenFlowLoader.pyc(3KB)
--------KITTIloader2012.pyc(2KB)
--------listflowfile.py(3KB)
--------KITTIloader.pyc(2KB)
--------KITTI_submission_loader2012.py(636B)
--------KITTIloader2012.py(969B)
--------SecenFlowLoader.py(2KB)
--------KITTI_submission_loader2012.pyc(1KB)
--------preprocess.pyc(7KB)
--------preprocess.py(5KB)
--------readpfm.py(914B)
----README.md(6KB)