A general imaging model and a method for finding its parameters

By M. Grossberg, Shree K. Nayar. Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, 2001

324 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The MOPED framework: Object recognition and pose estimation for manipulation (2011, methodology): “The techniques we consider are the generalized camera (Grossberg and Nayar 2001) and the pose averaging (Viksten et al.”
Using many cameras as one (2003, methodology): “A complete deﬁnition of the imaging model has been deﬁned in terms of “rax-els” [13], (see Figure 2).”
CosyPose: Consistent multi-view multi-object 6D pose estimation (2020, background): “Prior work using local invariant features includes [15,16,24,25] and involves some form of feature matching to establish correspondences across views to aggregate information from multiple viewpoints.”
Privacy Preserving Image-Based Localization (2019, methodology): “After Grossberg and Nayar [28] formulated the theory of generalized cameras, Pless [51] derived generalized epipolar constraints from the the Plücker representation of 3D lines.”
Efficient multi-view object recognition and full pose estimation (2010, background): “Some multi-view techniques for pose estimation parameterize a network of cameras as a single Generalized Camera[7] and optimize the camera pose over this generalized space by solving the resulting non-perspective PnP (nPnP) problem[12].”