Details
| Original language | English |
|---|---|
| Title of host publication | 13th International Fall Workshop Vision, Modeling, and Visualization 2008, VMV 2008 |
| Pages | 263-272 |
| Number of pages | 10 |
| Publication status | Published - 2008 |
| Externally published | Yes |
| Event | 13th International Fall Workshop Vision, Modeling, and Visualization 2008, VMV 2008 - Konstanz, Germany Duration: 8 Oct 2008 → 10 Oct 2008 |
Publication series
| Name | 13th International Fall Workshop Vision, Modeling, and Visualization 2008, VMV 2008 |
|---|
Abstract
Recent variational stereo approaches suffer from at least one of the following drawbacks: Either they use an isotropic disparity-driven smoothness term that ignores the directional information of the disparity field, or they apply anisotropic image-driven regularisation that suffers from oversegmen-tation artifacts. As a remedy, we present a novel anisotropic disparity-driven approach for stereo vision. It is designed as a highly adaptive anisotropic diffusion-reaction equation that incorporates a diffusion process which has been used successfully for image denoising and inpainting. Its directional adaptation allows to better control the smoothing w.r.t. the local structure of the disparity field. Experiments that compare our model to a recent isotropic variational method and a probabilistic graph cut approach demonstrate the superior quality of our approach. Moreover, a multigrid algorithm allows for moderate run times that do not depend on the disparity range.
ASJC Scopus subject areas
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Mathematics(all)
- Modelling and Simulation
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
13th International Fall Workshop Vision, Modeling, and Visualization 2008, VMV 2008. 2008. p. 263-272 (13th International Fall Workshop Vision, Modeling, and Visualization 2008, VMV 2008).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - PDE-based anisotropic disparity-driven stereo vision
AU - Zimmer, Henning
AU - Bruhn, Andrés
AU - Valgaerts, Levi
AU - Breuß, Michael
AU - Weickert, Joachim
AU - Rosenhahn, Bodo
AU - Seidel, Hans Peter
PY - 2008
Y1 - 2008
N2 - Recent variational stereo approaches suffer from at least one of the following drawbacks: Either they use an isotropic disparity-driven smoothness term that ignores the directional information of the disparity field, or they apply anisotropic image-driven regularisation that suffers from oversegmen-tation artifacts. As a remedy, we present a novel anisotropic disparity-driven approach for stereo vision. It is designed as a highly adaptive anisotropic diffusion-reaction equation that incorporates a diffusion process which has been used successfully for image denoising and inpainting. Its directional adaptation allows to better control the smoothing w.r.t. the local structure of the disparity field. Experiments that compare our model to a recent isotropic variational method and a probabilistic graph cut approach demonstrate the superior quality of our approach. Moreover, a multigrid algorithm allows for moderate run times that do not depend on the disparity range.
AB - Recent variational stereo approaches suffer from at least one of the following drawbacks: Either they use an isotropic disparity-driven smoothness term that ignores the directional information of the disparity field, or they apply anisotropic image-driven regularisation that suffers from oversegmen-tation artifacts. As a remedy, we present a novel anisotropic disparity-driven approach for stereo vision. It is designed as a highly adaptive anisotropic diffusion-reaction equation that incorporates a diffusion process which has been used successfully for image denoising and inpainting. Its directional adaptation allows to better control the smoothing w.r.t. the local structure of the disparity field. Experiments that compare our model to a recent isotropic variational method and a probabilistic graph cut approach demonstrate the superior quality of our approach. Moreover, a multigrid algorithm allows for moderate run times that do not depend on the disparity range.
UR - http://www.scopus.com/inward/record.url?scp=77953216194&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:77953216194
SN - 9781586039219
T3 - 13th International Fall Workshop Vision, Modeling, and Visualization 2008, VMV 2008
SP - 263
EP - 272
BT - 13th International Fall Workshop Vision, Modeling, and Visualization 2008, VMV 2008
T2 - 13th International Fall Workshop Vision, Modeling, and Visualization 2008, VMV 2008
Y2 - 8 October 2008 through 10 October 2008
ER -