We present an improved model for MRF-based depth upsampling, guided by image-as well as 3D surface normal features. By exploiting the underlying camera model we define a novel regularization term that implicitly evaluates the planarity of arbitrary oriented surfaces. Our method improves upsampling quality in scenes composed of predominantly planar surfaces, such as urban areas. We use a synthetic dataset to demonstrate that our approach outperforms recent methods that implement distance-based regularization terms. Finally, we validate our approach for mapping applications on our experimental vehicle.
Guided depth upsampling for precise mapping of urban environments
2017 IEEE Intelligent Vehicles Symposium (IV) ; 1140-1145
01.06.2017
1684904 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Guided Depth Upsampling for Precise Mapping of Urban Environments
British Library Conference Proceedings | 2017
|Image-guided ToF depth upsampling: a survey
British Library Online Contents | 2017
|Enhancement of dynamic depth scenes by upsampling for precise super-resolution (UP-SR)
British Library Online Contents | 2016
|