GA-Net: Guided Aggregation Net for End-To-End Stereo Matching
University of Oxford · Baidu (China)
Abstract
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…
Citation impact
- FWCI
- 40.32
- Percentile
- 100%
- References
- 43
Authors
4Topics & keywords
- Computer science
- Convolutional neural network
- Layer (electronics)
- Block (permutation group theory)
- End-to-end principle
- Matching (statistics)
- Net (polyhedron)
- Task (project management)