Evaluation of Stereo Matching Costs on Images with Radiometric Differences

By Heiko Hirschmüller, Daniel Scharstein. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009

785 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d5b695242697d5c6a48f667a3a1bd6817e8ce331

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

Citations in the corpus

SegStereo: Exploiting Semantic Information for Disparity Estimation (2018, background): “They either formulate the task as supervised learning [26,22] based on current labeled dataset [14,41],”
Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches (2015, methodology): “Following Hirschm¨uller and Scharstein (2009) we refer to the ﬁrst two steps as computing the matching cost and the last two steps as the stereo method.”
REMODE: Probabilistic, monocular dense reconstruction in real time (2014, background): “The literature in dense stereo is vast and we refer to [9] for a comparison.”
High-Resolution Stereo Datasets with Subpixel-Accurate Ground Truth (2014, background): “Stereo vision is one of the most heavily researched topics in computer vision [5, 17, 18, 20, 28], and much of the progress over the last decade has been driven by the availability of standard test images and benchmarks [7, 14, 27, 28, 30, 31].”
Constant Time Weighted Median Filtering for Stereo Matching and Beyond (2013, background): “As a byproduct, the fast weighted median filtering unleashes its potential in other applications that were hampered by high complexities.”
Multi-View Stereo: A Tutorial (2015, background): “We point interested readers to [99] for a detailed review.”
State of the art in high density image matching (2014, methodology): “The reader is instead referred to surveys and comparisons of matching algorithms presented in Makarovic (1992), Scharstein and Szeliski (2002), Brown et al. (2003), Seitz et al. (2006), Hirschm € uller and Scharstein (2009) and Gruen (2012).”
On building an accurate stereo matching system on graphics hardware (2011, background): “In a recent evaluation by Hirschmüller and Scharstein [3], census shows the best overall results in local and global stereo matching methods.”
Stereo vision based indoor/outdoor navigation for flying robots (2013, methodology): “The Hamming distance of Census transformed images is used as matching cost [12], since it offers a high radiometric robustness that is needed for processing real images [13].”
Intel RealSense Stereoscopic Depth Cameras (2017, methodology): “Thorough comparisons of photometric correlation methods showed the Census descriptor to be among the most robust to handling noisy imagining environments [9].”
Computing the stereo matching cost with a convolutional neural network (2014, methodology): “Following Hirschmuller and Scharstein (2009), we refer to steps (1) and (2) as computing the matching cost and steps (3) and (4) as the stereo method.”