Adaptive Structure from Motion with a contrario model estimation

Pierre Moulon (1, 2, 3) , Pascal Monasse (1, 2, 3) , Renaud Marlet (1, 2, 3, 4)

1 imagine [Marne-la-Vallée]
2 ENPC - École des Ponts ParisTech
3 LIGM - Laboratoire d'Informatique Gaspard-Monge
4 UPEM - Université Paris-Est Marne-la-Vallée

Structure from Motion (SfM) algorithms take as input multi-view stereo images (along with internal calibration information) and yield a 3D point cloud and camera orientations/poses in a common 3D coordinate system. In the case of an incremental SfM pipeline, the process requires repeated model estimations based on detected feature points: homography, fundamental and essential matrices, as well as camera poses. These estimations have a crucial impact on the quality of 3D reconstruction. We propose to improve these estimations using the a contrario methodology. While SfM pipelines usually have globally-fixed thresholds for model estimation, the a contrario principle adapts thresholds to the input data and for each model estimation. Our experiments show that adaptive thresholds reach a significantly better precision. Additionally, the user is free from having to guess thresholds or to optimistically rely on default values. There are also cases where a globally-fixed threshold policy, whatever the threshold value is, cannot provide the best accuracy, contrary to an adaptive threshold policy.

Mots clés: Structure from Motion; robust estimation; computer vision

Domaines: Informatique et théorie des jeux [cs.GT]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Pierre Moulon, Pascal Monasse, Renaud Marlet. Adaptive Structure from Motion with a contrario model estimation. ACCV 2012, Nov 2012, Daejeon, South Korea. pp.257-270, ⟨10.1007/978-3-642-37447-0_20⟩. ⟨hal-00769266⟩