Ensemble Learning for Confidence Measures in Stereo Vision
By Ralf Haeusler, Rahul Nair, Daniel Kondermann. 2013
123 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Media Technology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Raquel Urtasun
- Mohammed Bennamoun
- Luc Van Gool
- Dacheng Tao
- Alexander Gerhard Schwing
- Xiaogang Wang
- Ming-Hsuan Yang
- Alan L. Yuille
In Media Technology
- Raquel Urtasun
- Alexander Gerhard Schwing
- Wenjie Luo
- Stefano Mattoccia
- Fabio Tosi
- K. Sohn
- Mohammed Bennamoun
- Seungryong Kim
Citations in the corpus
- Learning to Detect Ground Control Points for Improving the Accuracy of Stereo Matching (2014, background): “They used horizontal intensity gradients features, but they had low importance scores.”
- Efficient Deep Learning for Stereo Matching (2016, methodology): “, by combining several confidence measures via a random forest classifier [14], or by incorporating random forest predictions into a Markov random field [23].”
- A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation (2020, methodology): “[104] fed a random forest with a pool of 23 confidence maps, estimated using conventional techniques, yielding a much better accuracy compared to any confidence map in the pool.”
- Intel RealSense Stereoscopic Depth Cameras (2017, background): “Raw costs are poorly correlated with matching quality, and aggregation of multiple features into combined threshold is a classification problem [6, 19].”
- Real-Time Self-Adaptive Deep Stereo (2018, background): “Early attempts to leverage machine learning for stereo matching concerned estimating confidence measures [31], by random forest classifiers [12, 38, 26, 28] and – later – by CNNs [29, 36, 42], typically plugged into conventional pipelines to improve accuracy.”
- LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation (2019, methodology): “To evaluate the performance of confidence estimation quantitatively, we used the sparsification curve and its area under curve (AUC) as used in [8, 39, 27, 37, 21].”
- End-to-End Learning of Geometry and Context for Deep Stereo Regression (2017, unknown): “Such confidence measures can improve the result of SGM as shown by Park and Yoon [37].”