A multi-block-matching approach for stereo
By Nils Einecke, Julian Eggert. 2015
44 citations recorded by the source corpus.
Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Aerospace Engineering
- Daniel Cremers
- Thomas Brox
- Andreas Geiger
- Wenjie Luo
- Alex Kendall
- Eddy Ilg
- Alexey Dosovitskiy
- Alexander Gerhard Schwing
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Jitendra Malik
- Andrea Vedaldi
- Ming-Hsuan Yang
- Xiaogang Wang
- Raquel Urtasun
- Andrew Zisserman
Citations in the corpus
- A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation (2015, methodology): “The network achieves an error that is ∼30% lower than the best real-time method reported in the table, Multi-BlockMatching [7].”
- Efficient Deep Learning for Stereo Matching (2016, background): “Again, we observe that our algorithm suffers from texture-less regions as well as regions with repetitive patterns.”
- End-to-End Learning of Geometry and Context for Deep Stereo Regression (2017, methodology): “For this reason, these algorithms do not use end-to-end learning and typically post-process the unary output with SGM regularization [11] to produce the final disparity maps.”