Evaluation of Cost Functions for Stereo Matching

By Heiko Hirschmüller, Daniel Scharstein. 2007

1,267 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

IRS: A Large Synthetic Indoor Robotics Stereo Dataset for Disparity and Surface Normal Estimation (2019, background): “MiddleBury is a well-known and frequently updated real world stereo dataset [23], [10], [11], [24], [12], which takes the resolution, brightness, exposure and many other uncommon factors into consideration to improve the complexities of the dataset and provides dense per-pixel disparities of the sce”
Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches (2015, methodology): “The data sets were published in ﬁve separate works in the years 2001, 2003, 2005, 2006, and 2014 (Scharstein and Szeliski, 2002, 2003; Scharstein and Pal, 2007; Hirschm¨uller and Scharstein, 2007; Scharstein et al., 2014).”
Exploiting the Power of Stereo Confidences (2013, methodology): “Further, we employ the Census metric as investigated by [11].”
High-Accuracy Stereo Matching Based on Adaptive Ground Control Points (2015, background): “Measurements of MI, NCC and CENSUS presented by [42] could only solve these problems partly and need further improvements.”
Deep Joint Image Filtering (2016, methodology): “Methods Middlebury [30,31] Lu [28] NYU v2 [26] SUN RGB/D [29] 4× 8× 16× 4× 8× 16× 4× 8× 16× 4× 8× 16× Bicubic 4.”
AOD-Net: All-in-One Dehazing Network (2017, methodology): “We also take the 800 full-size synthetic images from the Middlebury stereo database [19, 18, 9] as the TestSet B.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “Usually, a separate context model is learned to handle occlusions, see Hoiem et al. (2008); Tu & Bai (2010); Desai et al.”
Single Image Dehazing via Multi-scale Convolutional Neural Networks (2016, methodology): “In addition, we generate a validation set of 50 synthesized hazy images using the Middlebury stereo database [34,35,36].”
Efficient Large-Scale Stereo Matching (2010, background): “We refer the reader to [24, 2] for a comprehensive study of dissimilarity metrics for stereo matching.”
Image Guided Depth Upsampling Using Anisotropic Total Generalized Variation (2013, methodology): “An exhaustive evaluation of our method in terms of quantitative and qualitative comparison is made using input images from the Middlebury datasets [10] [20].”
Dehazing Using Color-Lines (2014, methodology): “[2009], and Kim et al. [2013] and used them to compare our method with the methods of He et al.”
MVSNet: Depth Inference for Unstructured Multi-view Stereo (2018, methodology): “Rather than using traditional handcrafted image features and matching metrics [28], recent studies on stereo apply the deep learning technique for better pair-wise patch matching.”
A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos (2017, background): “Indeed, the advent of excellent datasets and benchmarks, such as [6,12,17,29,32–34,38,40], has greatly advanced the state of the art of stereo and multi-view stereo (MVS) techniques.”
Learning for Disparity Estimation Through Feature Constancy (2017, neutral): “The four-step pipeline dominants existing stereo matching algorithms [24, 22, 9, 21], while each of its steps is important to the overall stereo matching performance.”
Robust stereo matching with surface normal prediction (2017, methodology): “We evaluate our method on both indoor stereo data captured by ourselves and the public Middlebury stereo dataset [29], [30], [18], [28].”
Review of Stereo Vision Algorithms: From Software to Hardware (2008, background): “Evaluation of various matching costs can be found in (Scharstein and Szeliski 2002; Mayoral et al. 2004; Hirschmuller and Scharstein 2007).”
Multi-View Stereo: A Tutorial (2015, background): “Census [206] is one of the best performers for stereo correspondences [100].”