Enhancing pose estimation through efficient patch synthesis

Pierre Rolin (1) , Marie-Odile Berger (1) , Frédéric Sur (1)

1 MAGRIT - Visual Augmentation of Complex Environments

Estimating the pose of a camera from a scene model is a challenging problem when the camera is in a position not covered by the views used to build the model, because feature matching is difficult. Several viewpoint simulation techniques have been recently proposed in this context. They generally come with a high computational cost, are limited to specific scenes such as urban environments or object-centred scenes, or need an initial pose guess. This paper presents a viewpoint simulation method well suited to most scenes and query views. Two major problems are addressed: the positioning of the virtual viewpoints with respect to the scene, and the synthesis of geometrically consistent patches. Experiments show that patch synthesis dramatically improves the accuracy of the pose in case of difficult registration, with a limited computational cost.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Pierre Rolin, Marie-Odile Berger, Frédéric Sur. Enhancing pose estimation through efficient patch synthesis. 27th British Machine Vision Conference (BMVC 2016), Sep 2016, York, United Kingdom. ⟨hal-01368843⟩