DAISY: An Efficient Dense Descriptor Applied for Wide Baseline Stereo
We show that it is possible to estimate depth from two wide baseline images
using a dense descriptor. Our local descriptor, called DAISY, is very fast
and efficient to compute. It depends on histograms of gradients like SIFT
and GLOH but uses a Gaussian weighting and circularly symmetrical
kernel. This gives us our speed and efficiency for dense computations. We
compute 200-length descriptors for every pixel in an 800x600 image in less
than 5 seconds.
Herz-Jesu Grid. By using two images, one from the left-most column and one
from the upper row, we compute depth and occlusion maps from the view point of
the row image. In the diagonal, we display the ground truth depth maps. We
marked the correctly detected occlusions with green, incorrectly detected ones
with blue and the missed ones with red. From this Figure, it is apparent that
DAISY can handle quite large baselines without losing too much from its
accuracy.
Stereo reconstructions obtained using the DAISY descriptor. The first row are
the input images where we use the first image and one of the other images as
input and the second row shows the respective reconstructions where the first
one is the laser scanned ground truth image.
Performance of DAISY against various transformations: Contrast+Rotation, Zoom,
Blur and Viewpoint chage.
Data
you can download the images that we've used in the publications from
here. archive contains all the images with calibrations and the groundtruth
depth maps used in the experiments. please give a reference to the papers if
you use the data in the set. additionally, if you're using the ground truth
depth maps, you need to cite mvs site too.
daisy-v1.8.1 // Sunday, October 11, 2009 11:42:22 +0200
MATLAB Code
USAGE-MATLABmdaisy-v1.0 // Wednesday, March 18, 2009 23:48:22 +0100 DAISY has a matlab implementation now.
References
DAISY: An Efficient Dense Descriptor Applied to Wide
Baseline Stereo
Engin Tola, Vincent Lepetit, Pascal Fua IEEE Transactions on Pattern Analysis and Machine Intelligence
May 2010 website
| pdf
| slides (9.5MB)
|
@article{Tola10,
author = "E. Tola and V. Lepetit and P. Fua",
title = {{DAISY: An Efficient Dense Descriptor Applied to Wide
Baseline Stereo}},
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
year = 2010,
month = "May",
pages = "815--830",
volume = "32",
number = "5"
}
A Fast Local Descriptor for Dense Matching
Engin Tola, Vincent Lepetit, Pascal Fua Proceedings of Computer Vision and Pattern Recognition 2008, Alaska, USA
June 2008 website
| pdf
| slides (9.5MB)
|
@inproceedings{Tola08,
author = "E. Tola and V.Lepetit and P. Fua",
title = {{A Fast Local Descriptor for Dense Matching}},
booktitle = "Proceedings of Computer Vision and Pattern Recognition",
year = 2008,
address = "Alaska, USA"
}
