Abstract
Symmetries and repetitions are common and valuable features in urban scenes. We propose to leverage such regularity information in an efficient optimization scheme in order to segment a rectified image of a facade into semantic categories. Our method retrieves a parsing which respects common architectural constraints as well as detected repetitive structures and edge information. Additionally, the use of symmetry information allows us to efficiently deal with large occluded areas and to recover plausible facade images with a minimum of occlusions. Our approach yields state-of-The-Art accuracy on datasets with challenging occlusions. Competitive works either fully fail to deal with large occlusions or they are an order of magnitude slower than our approach.
Original language | English (US) |
---|---|
Title of host publication | Proceedings - 2017 International Conference on 3D Vision, 3DV 2017 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 393-401 |
Number of pages | 9 |
ISBN (Electronic) | 9781538626108 |
DOIs | |
State | Published - May 25 2018 |
Event | 7th IEEE International Conference on 3D Vision, 3DV 2017 - Qingdao, China Duration: Oct 10 2017 → Oct 12 2017 |
Publication series
Name | Proceedings - 2017 International Conference on 3D Vision, 3DV 2017 |
---|
Other
Other | 7th IEEE International Conference on 3D Vision, 3DV 2017 |
---|---|
Country | China |
City | Qingdao |
Period | 10/10/17 → 10/12/17 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Media Technology
- Computer Vision and Pattern Recognition
- Signal Processing
Cite this
}
Symmetry-Aware façade parsing with occlusions. / Cohen, Andrea; Oswald, Martin R.; Liu, Yanxi; Pollefeys, Marc.
Proceedings - 2017 International Conference on 3D Vision, 3DV 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 393-401 (Proceedings - 2017 International Conference on 3D Vision, 3DV 2017).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Symmetry-Aware façade parsing with occlusions
AU - Cohen, Andrea
AU - Oswald, Martin R.
AU - Liu, Yanxi
AU - Pollefeys, Marc
PY - 2018/5/25
Y1 - 2018/5/25
N2 - Symmetries and repetitions are common and valuable features in urban scenes. We propose to leverage such regularity information in an efficient optimization scheme in order to segment a rectified image of a facade into semantic categories. Our method retrieves a parsing which respects common architectural constraints as well as detected repetitive structures and edge information. Additionally, the use of symmetry information allows us to efficiently deal with large occluded areas and to recover plausible facade images with a minimum of occlusions. Our approach yields state-of-The-Art accuracy on datasets with challenging occlusions. Competitive works either fully fail to deal with large occlusions or they are an order of magnitude slower than our approach.
AB - Symmetries and repetitions are common and valuable features in urban scenes. We propose to leverage such regularity information in an efficient optimization scheme in order to segment a rectified image of a facade into semantic categories. Our method retrieves a parsing which respects common architectural constraints as well as detected repetitive structures and edge information. Additionally, the use of symmetry information allows us to efficiently deal with large occluded areas and to recover plausible facade images with a minimum of occlusions. Our approach yields state-of-The-Art accuracy on datasets with challenging occlusions. Competitive works either fully fail to deal with large occlusions or they are an order of magnitude slower than our approach.
UR - http://www.scopus.com/inward/record.url?scp=85048832529&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048832529&partnerID=8YFLogxK
U2 - 10.1109/3DV.2017.00052
DO - 10.1109/3DV.2017.00052
M3 - Conference contribution
AN - SCOPUS:85048832529
T3 - Proceedings - 2017 International Conference on 3D Vision, 3DV 2017
SP - 393
EP - 401
BT - Proceedings - 2017 International Conference on 3D Vision, 3DV 2017
PB - Institute of Electrical and Electronics Engineers Inc.
ER -