Simultaneous Multi-view Relative Pose Estimation and 3D Reconstruction from Planar Regions (bibtex)
by Robert Frohlich, Zoltan Kato
Abstract:
In this paper, we propose a novel solution for multi-view reconstruction, relative pose and homography estimation using planar regions. The proposed method doesn`t require point matches, it directly uses a pair of planar image regions and simultaneously reconstructs the normal and distance of the corresponding 3D planar surface patch, the relative pose of the cameras as well as the aligning homography between the image regions. When more than two cameras are available, then a special region-based bundle adjustment is proposed, which provides robust estimates in a multi-view camera system by constructing and solving a non-linear system of equations. The method is quantitatively evaluated on a large synthetic dataset as well as on the KITTI vision benchmark dataset.
Reference:
Robert Frohlich, Zoltan Kato, Simultaneous Multi-view Relative Pose Estimation and 3D Reconstruction from Planar Regions, In Proceedings of ACCV Workshop on Advanced Machine Vision for Real-life and Industrially Relevant Applications (Gustavo Carneiro, Shaodi You, eds.), volume 11367 of Lecture Notes in Computer Science, Perth, Australia, pp. 467-483, 2018, Springer.
Bibtex Entry:
@string{accvamv="Proceedings of ACCV Workshop on Advanced Machine Vision for Real-life and Industrially Relevant Applications"}
@string{lncs="Lecture Notes in Computer Science"}
@string{springer="Springer"}
@InProceedings{Frohlich-Kato2018,
  author    = {Frohlich, Robert and Kato, Zoltan},
  title     = {Simultaneous Multi-view Relative Pose Estimation and {3D} Reconstruction from Planar Regions},
  booktitle = accvamv,
  year      = {2018},
  editor    = {Carneiro, Gustavo and You, Shaodi},
  volume    = {11367},
  series    = lncs,
  pages     = {467--483},
  address   = {Perth, Australia},
  month     = dec,
  publisher = {Springer},
  abstract  = {In this paper, we propose a novel solution for multi-view reconstruction, relative pose and homography estimation using planar regions. The proposed method doesn`t require point matches, it directly uses a pair of planar image regions and simultaneously reconstructs the normal and distance of the corresponding 3D planar surface patch, the relative pose of the cameras as well as the aligning homography between the image regions. When more than two cameras are available, then a special region-based bundle adjustment is proposed, which provides robust estimates in a multi-view camera system by constructing and solving a non-linear system of equations. The method is quantitatively evaluated on a large synthetic dataset as well as on the KITTI vision benchmark dataset.},
}
Powered by bibtexbrowser