Synthezising Real World Stereo Challenges
Creators
-
1.
University of Auckland
- 2. Heidelberg Collaboratory for Image Processing (HCI)
-
3.
Heidelberg University
Description
Abstract
On this page, we provide datasets discussed in the paper: Synthezising Real World Stereo Challenges. With these datasets, we aim at isolating specific challenges for stereo matchers. Previous synthetic datasets did not seperate different problematic issues in stereo analysis.
Technical info
Datasets
We generated four datasets, addressing textureless areas, foreground fattening, decalibration and visual artifacts. To each dataset different levels (none, slight, strong) of white Gaussian noise are applied.
Textureless
A slanted planar surface, with diminishing texture towards the image center.
Preview Image: [link]
![[link]](../records/8032802/preview/textureless.png?include_deleted=0){kind=link}
Foreground fattening
Thin foreground objects. Background texture is diminishing towards the right image border.
Preview Image: [link]
![[link]](../records/8032802/preview/foreground_fattening.png?include_deleted=0){kind=link}
Decalibration
A gradient of vertical and horizontal texture. The match image is rotated slightly around the image center.
Preview Image: [link]
![[link]](../records/8032802/preview/decalibration.png?include_deleted=0){kind=link}
Visual artifacts
A slanted planar surface. Blocks of different thickness and transparency are introduced to the left view.
Preview Image: [link]
![[link]](../records/8032802/preview/visual_artifacts.png?include_deleted=0){kind=link}
Ground truth
We provide ground truth as 16 bit graylevel pgm files. Disparities in pixel units are obtained by dividing the 16bit value by 256.
Notes
Acknowledgements
Created by Ralf Haeusler
Files
StereoTestSynth.zip
Files
(7.1 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:73cf5adda457b7e4b8277e42cb03f339
|
120.0 kB | Preview Download |
|
md5:cbf7f9118634d3e89e6e2950864f7610
|
120.7 kB | Preview Download |
|
md5:ec5bdfb0ba4590415571112827194074
|
6.6 MB | Preview Download |
|
md5:f837622ceb53f1fce914befe858c2456
|
105.0 kB | Preview Download |
|
md5:0134165ba4c29f371fc8130c85ed3419
|
129.7 kB | Preview Download |
Additional details
Related works
- Is described by
- Conference proceeding: 10.1007/978-3-642-40602-7_17 (DOI)
- Obsoletes
- Dataset: https://hci.iwr.uni-heidelberg.de/benchmarks/Synthezising_Real_World_Stereo_Challenges (URL)
- Dataset: http://hci.iwr.uni-heidelberg.de//Benchmarks/document/synthesizing_stereo_challenges/ (URL)
References
- Haeusler, R., Kondermann, D. (2013). Synthesizing Real World Stereo Challenges. In: Weickert, J., Hein, M., Schiele, B. (eds) Pattern Recognition. GCPR 2013. Lecture Notes in Computer Science, vol 8142. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40602-7_17