Middlebury Stereo
Others
Stereo Matching
|...
许可协议: Unknown

Overview

The Muddlebury Stereo Dataset is collected under the support of Middlebury College.The dataset is developed for online evaluation dense two-frame stereo algorithms.

Data Format

2001 Stereo datasets with ground truth

These datasets of piecewise planar scenes were created by Daniel Scharstein, Padma Ugbabe, and Rick Szeliski. Each set contains 9 images (im0.ppm - im8.ppm) and ground-truth disparity maps for images 2 and 6 (disp2.pgm and disp6.pgm). Each ground-truth disparity map is scaled by a factor of 8. For example, a value of 100 in disp2.pgm means that the corresponding pixel in im6.ppm is 12.5 pixels to the left.

2003 Stereo datasets with ground truth

These datasets were created by Daniel Scharstein, Alexander Vandenberg-Rodes, and Rick Szeliski. They consist of high-resolution stereo sequences with complex geometry and pixel-accurate ground-truth disparity data. The ground-truth disparities are acquired using a novel technique that employs structured lighting and does not require the calibration of the light projectors. See our CVPR 2003 paper for more details.

Quarter-size (450 x 375) versions of our new data sets "Cones" and "Teddy" are available for download. Each data set contains 9 color images (im0..im8) and 2 disparity maps (disp2 and disp6). The 9 color images form a multi-baseline stereo sequence, i.e., they are taken from equally-spaced viewpoints along the x-axis from left to right. The images are rectified so that all image motion is purely horizontal. To test a two-view stereo algorithm, the two reference views im2 (left) and im6 (right) should be used. Ground-truth disparites with quarter-pixel accuracy are provided for these two views. Disparities are encoded using a scale factor 4 for gray levels 1 .. 255, while gray level 0 means "unknown disparity". Therefore, the encoded disparity range is 0.25 .. 63.75 pixels.

2005 Stereo datasets with ground truth

These 9 datasets were created by Anna Blasiak, Jeff Wehrwein, and Daniel Scharstein at Middlebury College in the summer of 2005, and were published in conjunction with two CVPR 2007 papers [3, 4]. Each image below links to a directory containing the full-size views and disparity maps. Shown are the left views; moving the mouse over the images shows the right views. We're withholding the true disparity maps for three of the sequences (Computer, Drumsticks, and Dwarves) which we may use in future evaluations.

Art Books Dolls
img img img
img img img
Laundry Moebius Reindeer
img img img
img img img
Computer Drumsticks Dwarves
img img img
img img img

2006 Stereo datasets with ground truth

These 21 datasets were created by Brad Hiebert-Treuer, Sarri Al Nashashibi, and Daniel Scharstein at Middlebury College in the summer of 2006, and were published in conjunction with two CVPR 2007 papers [3, 4]. Each image below links to a directory containing the full-size views and disparity maps. Shown are the left views; moving the mouse over the images shows the right views.

Aloe Baby1 Baby2
img img img
img img img

2014 Stereo datasets with ground truth

These 33 datasets were created by Nera Nesic, Porter Westling, Xi Wang, York Kitajima, Greg Krathwohl, and Daniel Scharstein at Middlebury College during 2011-2013, and refined with Heiko Hirschmüller at the DLR Germany during 2014. A detailed description of the acquisition process can be found in GCPR 2014 paper.

20 of the datasets are used in the new Middlebury Stereo Evaluation (10 each for training and test sets). Except for the 10 test datasets, we provide links to directories containing the full-size views and disparity maps. Shown are the left views at 5% resolution; moving the mouse over the images shows the right views.

10 evaluation test sets (GT hidden)
Australia img img Bicycle2 img img Classroom2 img img Crusade img img Djembe img img
Hoops img img Livingroom img img Newkuba img img Plants img img Staircase img img
10 evaluation training sets with GT
Adirondack: perf, imp img img Jadeplant: perf, imp img img Motorcycle: perf, imp img img Piano: perf, imp img img Pipes: perf, imp img img
Playroom: perf, imp img img Playtable: perf, imp img img Recycle: perf, imp img img Shelves: perf, imp img img Vintage: perf, imp img img
13 additional datasets with GT
Backpack: perf, imp img img Bicycle1: perf, imp img img Cable: perf, imp img img Classroom1: perf, imp img img Couch: perf, imp img img
Flowers: perf, imp img img Mask: perf, imp img img Shopvac: perf, imp img img Sticks: perf, imp img img Storage: perf, imp img img
Sword1: perf, imp img img Sword2: perf, imp img img Umbrella: perf, imp img img

Citation

Please use the following citation when referencing the dataset:

@inproceedings{inproceedings,
author = {Scharstein, Daniel and Szeliski, Richard and Zabih, Ramin},
year = {2001},
month = {02},
pages = {131-140},
title = {A taxonomy and evaluation of dense two-frame stereo correspondence algorithm},
volume = {47},
isbn = {0-7695-1327-1},
journal = {Int. J. Comput. Vision},
doi = {10.1109/SMBV.2001.988771}
}
数据概要
数据格式
Image,
数据量
--
文件大小
--
发布方
Middlebury College
Middlebury College is a private liberal arts college in Middlebury, Vermont.
数据集反馈
| 6 | 数据量 -- | 大小 --
Middlebury Stereo
Others
Stereo Matching
许可协议: Unknown

Overview

The Muddlebury Stereo Dataset is collected under the support of Middlebury College.The dataset is developed for online evaluation dense two-frame stereo algorithms.

Data Format

2001 Stereo datasets with ground truth

These datasets of piecewise planar scenes were created by Daniel Scharstein, Padma Ugbabe, and Rick Szeliski. Each set contains 9 images (im0.ppm - im8.ppm) and ground-truth disparity maps for images 2 and 6 (disp2.pgm and disp6.pgm). Each ground-truth disparity map is scaled by a factor of 8. For example, a value of 100 in disp2.pgm means that the corresponding pixel in im6.ppm is 12.5 pixels to the left.

2003 Stereo datasets with ground truth

These datasets were created by Daniel Scharstein, Alexander Vandenberg-Rodes, and Rick Szeliski. They consist of high-resolution stereo sequences with complex geometry and pixel-accurate ground-truth disparity data. The ground-truth disparities are acquired using a novel technique that employs structured lighting and does not require the calibration of the light projectors. See our CVPR 2003 paper for more details.

Quarter-size (450 x 375) versions of our new data sets "Cones" and "Teddy" are available for download. Each data set contains 9 color images (im0..im8) and 2 disparity maps (disp2 and disp6). The 9 color images form a multi-baseline stereo sequence, i.e., they are taken from equally-spaced viewpoints along the x-axis from left to right. The images are rectified so that all image motion is purely horizontal. To test a two-view stereo algorithm, the two reference views im2 (left) and im6 (right) should be used. Ground-truth disparites with quarter-pixel accuracy are provided for these two views. Disparities are encoded using a scale factor 4 for gray levels 1 .. 255, while gray level 0 means "unknown disparity". Therefore, the encoded disparity range is 0.25 .. 63.75 pixels.

2005 Stereo datasets with ground truth

These 9 datasets were created by Anna Blasiak, Jeff Wehrwein, and Daniel Scharstein at Middlebury College in the summer of 2005, and were published in conjunction with two CVPR 2007 papers [3, 4]. Each image below links to a directory containing the full-size views and disparity maps. Shown are the left views; moving the mouse over the images shows the right views. We're withholding the true disparity maps for three of the sequences (Computer, Drumsticks, and Dwarves) which we may use in future evaluations.

Art Books Dolls
img img img
img img img
Laundry Moebius Reindeer
img img img
img img img
Computer Drumsticks Dwarves
img img img
img img img

2006 Stereo datasets with ground truth

These 21 datasets were created by Brad Hiebert-Treuer, Sarri Al Nashashibi, and Daniel Scharstein at Middlebury College in the summer of 2006, and were published in conjunction with two CVPR 2007 papers [3, 4]. Each image below links to a directory containing the full-size views and disparity maps. Shown are the left views; moving the mouse over the images shows the right views.

Aloe Baby1 Baby2
img img img
img img img

2014 Stereo datasets with ground truth

These 33 datasets were created by Nera Nesic, Porter Westling, Xi Wang, York Kitajima, Greg Krathwohl, and Daniel Scharstein at Middlebury College during 2011-2013, and refined with Heiko Hirschmüller at the DLR Germany during 2014. A detailed description of the acquisition process can be found in GCPR 2014 paper.

20 of the datasets are used in the new Middlebury Stereo Evaluation (10 each for training and test sets). Except for the 10 test datasets, we provide links to directories containing the full-size views and disparity maps. Shown are the left views at 5% resolution; moving the mouse over the images shows the right views.

10 evaluation test sets (GT hidden)
Australia img img Bicycle2 img img Classroom2 img img Crusade img img Djembe img img
Hoops img img Livingroom img img Newkuba img img Plants img img Staircase img img
10 evaluation training sets with GT
Adirondack: perf, imp img img Jadeplant: perf, imp img img Motorcycle: perf, imp img img Piano: perf, imp img img Pipes: perf, imp img img
Playroom: perf, imp img img Playtable: perf, imp img img Recycle: perf, imp img img Shelves: perf, imp img img Vintage: perf, imp img img
13 additional datasets with GT
Backpack: perf, imp img img Bicycle1: perf, imp img img Cable: perf, imp img img Classroom1: perf, imp img img Couch: perf, imp img img
Flowers: perf, imp img img Mask: perf, imp img img Shopvac: perf, imp img img Sticks: perf, imp img img Storage: perf, imp img img
Sword1: perf, imp img img Sword2: perf, imp img img Umbrella: perf, imp img img

Citation

Please use the following citation when referencing the dataset:

@inproceedings{inproceedings,
author = {Scharstein, Daniel and Szeliski, Richard and Zabih, Ramin},
year = {2001},
month = {02},
pages = {131-140},
title = {A taxonomy and evaluation of dense two-frame stereo correspondence algorithm},
volume = {47},
isbn = {0-7695-1327-1},
journal = {Int. J. Comput. Vision},
doi = {10.1109/SMBV.2001.988771}
}
数据集反馈
0
立即开始构建AI
graviti
wechat-QR
长按保存识别二维码,关注Graviti公众号