Geometrically constrained structure from motion: points on planes

Conference item

Structure from motion algorithms typically do not use external geometric constraints, e.g., the coplanarity of certain points or known orientations associated with such planes, until a final post-processing stage. In this paper, we show how such geometric constraints can be incorporated early on in the reconstruction process, thereby improving the quality of the estimates. The approaches we study include hallucinating extra point matches in planar regions, computing fundamental matrices directly from homographies, and applying coplanarity and other geometric constraints as part of the final bundle adjustment stage. Our experimental results indicate that the quality of the reconstruction can be significantly improved by the judicious use of geometric constraints.

Authors: Szeliski, R; Torr, PHS

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer
• Host title: 3D Structure from Multiple Images of Large-Scale Environments
• Pages: 171-186
• Series: Lecture Notes in Computer Science
• Series number: 1506
• Publication date: 1998-11-30
• Event title: 3D Structure from Multiple Images of Large-Scale Environments, European Workshop (SMILE 1998)
• Event location: Freiburg, Germany
• Event start date: 1998-06-06
• Event end date: 1998-06-07
• DOI: 10.1007/3-540-49437-5_12
• EISSN: 1611-3349
• ISSN: 1611-3349
• EISBN: 9783540494379
• ISBN: 9783540653103
• Language: English
• Keywords: SBTMR