计算机科学
卷积神经网络
图层(电子)
块(置换群论)
端到端原则
匹配(统计)
网(多面体)
任务(项目管理)
人工神经网络
人工智能
可微函数
深度学习
计算复杂性理论
模式识别(心理学)
算法
数学
经济
有机化学
几何学
化学
管理
数学分析
统计
作者
Feihu Zhang,Victor Adrian Prisacariu,Ruigang Yang,Philip H. S. Torr
出处
期刊:Proceedings
[Institute of Electrical and Electronics Engineers]
日期:2019-06-01
卷期号:: 185-194
被引量:998
标识
DOI:10.1109/cvpr.2019.00027
摘要
In the stereo matching task, matching cost aggregation is crucial in both traditional methods and deep neural network models in order to accurately estimate disparities. We propose two novel neural net layers, aimed at capturing local and the whole-image cost dependencies respectively. The first is a semi-global aggregation layer which is a differentiable approximation of the semi-global matching, the second is the local guided aggregation layer which follows a traditional cost filtering strategy to refine thin structures. These two layers can be used to replace the widely used 3D convolutional layer which is computationally costly and memory-consuming as it has cubic computational/memory complexity. In the experiments, we show that nets with a two-layer guided aggregation block easily outperform the state-of-the-art GC-Net which has nineteen 3D convolutional layers. We also train a deep guided aggregation network (GA-Net) which gets better accuracies than state-of-the-art methods on both Scene Flow dataset and KITTI benchmarks.
科研通智能强力驱动
Strongly Powered by AbleSci AI