Pattern recognition (psychology)

Mathematics

Computer science

Management

Matching (statistics)

Differentiable function

Block (permutation group theory)

Economics

End-to-end principle

Algorithm

Deep learning

Organic chemistry

Artificial intelligence

Geometry

Layer (electronics)

Artificial neural network

Statistics

Mathematical analysis

Computational complexity theory

Chemistry

Task (project management)

Convolutional neural network

Net (polyhedron)

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 a...

GA-Net: Guided Aggregation Net for End-To-End Stereo Matching