Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Group-wise Correlation Stereo Network #18

Open
DeepTecher opened this issue Mar 13, 2019 · 0 comments
Open

Group-wise Correlation Stereo Network #18

DeepTecher opened this issue Mar 13, 2019 · 0 comments
Labels
CVPR 2019 论文速递 无人驾驶最新相关论文

Comments

@DeepTecher
Copy link
Owner

Group-wise Correlation Stereo Network

提交日期: 2019-03-10 (CVPR 2019)
团队:香港中文大学电子工程系、商汤科技
摘要:
立体匹配估计整流图像对之间的差异,这对深度感测、自动驾驶和其他相关任务非常重要。先前的工作建立了在所有视差水平上具有交叉相关或串联左右特征的成本量,然后利用2D或3D卷积神经网络来回归视差图。在本文中,我们建议通过分组相关来构建成本量。左边特征和右边特征沿着通道维度被分成组,并且在每个组之间计算相关图以获得多个匹配成本提议,然后将其打包到成本量中。分组相关为测量特征相似性提供了有效的表示,并且不会丢失过多的信息,如完全相关。与以前的方法相比,它在减少参数时也能保持更好的性能。在先前的工作中提出的3D堆叠沙漏网络被改进以提高性能并降低推理计算成本。实验结果表明,我们的方法在Scene Flow,KITTI 2012和KITTI 2015数据集上优于以前的方法。此代码可通过此URL(代码待更新)获得

@DeepTecher DeepTecher added 论文速递 无人驾驶最新相关论文 CVPR 2019 labels Mar 13, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CVPR 2019 论文速递 无人驾驶最新相关论文
Projects
None yet
Development

No branches or pull requests

1 participant