Details
| Original language | English |
|---|---|
| Title of host publication | Beiträge |
| Subtitle of host publication | 39. Wissenschaftlich-Technische Jahrestagung der DGPF e.V. |
| Editors | Thomas P. Kersten |
| Place of Publication | München |
| Pages | 363-374 |
| Number of pages | 12 |
| Publication status | Published - 2019 |
| Event | Dreiländertagung OVG-DGPF-SGPF: Photogrammetrie-Fernerkundung-Geoinformation - Universität für Bodenkultur Wien, Wien, Austria Duration: 20 Feb 2019 → 22 Feb 2019 https://dgpf.de/con/jt2019.html |
Publication series
| Name | Publikationen der Deutschen Gesellschaft für Photogrammetrie, Fernerkundung und Geoinformation e.V. |
|---|---|
| Publisher | Deutsche Gesellschaft für Photogrammetrie, Fernerkundung und Geoinformation e.V. |
| Volume | 28 |
| ISSN (Print) | 0942-2870 |
Abstract
ent information as a regularizer to preserve local structure details in large depth discontinuity areas. We evaluate our model in terms of end-point-error on several challenging stereo datasets such as Scene Flow, Sintel and KITTI. Experimental results demonstrate that our model achieves better performance than DispNet on most datasets (e.g. we obtain an improvement of 36% on Sintel) and estimates better structure-preserving disparity maps. Moreover, our
proposal also achieves competitive performance compared to other methods.
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Beiträge: 39. Wissenschaftlich-Technische Jahrestagung der DGPF e.V.. ed. / Thomas P. Kersten. München, 2019. p. 363-374 (Publikationen der Deutschen Gesellschaft für Photogrammetrie, Fernerkundung und Geoinformation e.V.; Vol. 28).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research
}
TY - GEN
T1 - Encoder-Decoder network for local structure preserving stereo matching
AU - Kang, Junhua
AU - Chen, Lin
AU - Deng, Fei
AU - Heipke, Christian
N1 - Funding Information: The author Junhua Kang would like to thank the China Scholarship Council (CSC) for financially supporting her as a visiting PhD student at Leibniz University Hannover, Germany. We gratefully acknowledge the support of NVIDIA Corporation with the donation of GPUs used for this research.
PY - 2019
Y1 - 2019
N2 - After many years of research, stereo matching remains to be a challenging task in photogrammetry and computer vision. Recent work has shown great progress by formulating dense stereo matching as a pixel-wise learning task to be resolved with a deep convolutional neural network (CNN). In this paper we investigate a recently proposed end-to-end disparity learning network, DispNet (MAYER et al. 2015), and improve it to yield better results in some problematic areas. The improvements consist in two major contributions. First, in order to handle large disparities, we modify the correlation module to construct the matching cost volume with patch-based correlation. We also modify the basic encoder-decoder module to regress detailed disparity images with full resolution. Second, instead of using post-processing steps to impose smoothness and handle depth discontinuities, we incorporate disparity gradi-ent information as a regularizer to preserve local structure details in large depth discontinuity areas. We evaluate our model in terms of end-point-error on several challenging stereo datasets such as Scene Flow, Sintel and KITTI. Experimental results demonstrate that our model achieves better performance than DispNet on most datasets (e.g. we obtain an improvement of 36% on Sintel) and estimates better structure-preserving disparity maps. Moreover, ourproposal also achieves competitive performance compared to other methods.
AB - After many years of research, stereo matching remains to be a challenging task in photogrammetry and computer vision. Recent work has shown great progress by formulating dense stereo matching as a pixel-wise learning task to be resolved with a deep convolutional neural network (CNN). In this paper we investigate a recently proposed end-to-end disparity learning network, DispNet (MAYER et al. 2015), and improve it to yield better results in some problematic areas. The improvements consist in two major contributions. First, in order to handle large disparities, we modify the correlation module to construct the matching cost volume with patch-based correlation. We also modify the basic encoder-decoder module to regress detailed disparity images with full resolution. Second, instead of using post-processing steps to impose smoothness and handle depth discontinuities, we incorporate disparity gradi-ent information as a regularizer to preserve local structure details in large depth discontinuity areas. We evaluate our model in terms of end-point-error on several challenging stereo datasets such as Scene Flow, Sintel and KITTI. Experimental results demonstrate that our model achieves better performance than DispNet on most datasets (e.g. we obtain an improvement of 36% on Sintel) and estimates better structure-preserving disparity maps. Moreover, ourproposal also achieves competitive performance compared to other methods.
M3 - Conference contribution
T3 - Publikationen der Deutschen Gesellschaft für Photogrammetrie, Fernerkundung und Geoinformation e.V.
SP - 363
EP - 374
BT - Beiträge
A2 - Kersten, Thomas P.
CY - München
T2 - Dreiländertagung OVG-DGPF-SGPF
Y2 - 20 February 2019 through 22 February 2019
ER -