TY - GEN
T1 - Recovering correct reconstructions from indistinguishable geometry
AU - Heinly, Jared
AU - Dunn, Enrique
AU - Frahm, Jan Michael
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2015/2/6
Y1 - 2015/2/6
N2 - Structure-from-motion (SFM) is widely utilized to generate 3D reconstructions from unordered photo-collections. However, in the presence of non unique, symmetric, or otherwise indistinguishable structure, SFM techniques often incorrectly reconstruct the final model. We propose a method that not only determines if an error is present, but automatically corrects the error in order to produce a correct representation of the scene. We find that by exploiting the co-occurrence information present in the scene's geometry, we can successfully isolate the 3D points causing the incorrect result. This allows us to split an incorrect reconstruction into error-free sub-models that we then correctly merge back together. Our experimental results show that our technique is efficient, robust to a variety of scenes, and outperforms existing methods.
AB - Structure-from-motion (SFM) is widely utilized to generate 3D reconstructions from unordered photo-collections. However, in the presence of non unique, symmetric, or otherwise indistinguishable structure, SFM techniques often incorrectly reconstruct the final model. We propose a method that not only determines if an error is present, but automatically corrects the error in order to produce a correct representation of the scene. We find that by exploiting the co-occurrence information present in the scene's geometry, we can successfully isolate the 3D points causing the incorrect result. This allows us to split an incorrect reconstruction into error-free sub-models that we then correctly merge back together. Our experimental results show that our technique is efficient, robust to a variety of scenes, and outperforms existing methods.
KW - 3D scene correction
KW - Duplicate structure disambiguation
KW - Local clustering coefficient
KW - Structure from motion
UR - http://www.scopus.com/inward/record.url?scp=84925340299&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84925340299&partnerID=8YFLogxK
U2 - 10.1109/3DV.2014.84
DO - 10.1109/3DV.2014.84
M3 - Conference contribution
AN - SCOPUS:84925340299
T3 - Proceedings - 2014 International Conference on 3D Vision, 3DV 2014
SP - 377
EP - 384
BT - Proceedings - 2014 International Conference on 3D Vision, 3DV 2014
T2 - 2014 2nd International Conference on 3D Vision, 3DV 2014
Y2 - 8 December 2014 through 11 December 2014
ER -