Learning to Detect Ground Control Points for Improving the Accuracy of Stereo Matching

By Aristotle Spyropoulos, Nikos Komodakis, Philippos Mordohai. 2014

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

In Media Technology

Citations in the corpus

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches (2015, background): “Recent work (Haeusler et al., 2013; Spyropoulos et al., 2014) focused on estimating the confidence of the computed matching cost.”
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): “Most existing methods for stereo matching [10, 17, 45] cannot provide fully reliable results due to its challenging elements, thus several approaches [39, 27, 37, 18, 20] have presented an additional module to predict a conﬁdence Q i of the disparity D i .”
A Survey on Deep Learning Techniques for Stereo-Based Depth Estimation (2020, methodology): “Recent techniques are based on supervised learning [104], [105], [106], [107], [108], [109].”
Computing the stereo matching cost with a convolutional neural network (2014, methodology): “[15] trained a random forest classifier to predict the confidence of the matching cost and used the predictions as soft constraints in a Markov random field to decrease the error of the stereo method.”
Robust stereo matching with surface normal prediction (2017, background): “Conditional Random Field (CRF) framework, where disparity smoothness constraints only exist between neighbor pixels, and used as soft constraints in a global optimization framework to reduce the disparity ambiguity [32].”
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].”