Affine structure from motion.

By Jan J. Koenderink, Andrea J. Koenderink-van Doorn. 1991

How researchers see this paper

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

Citations in the corpus

Lifting Object Detection Datasets into 3D (2015, background): “While the popularity of model-based recognition was falling, interest in multiview 3D reconstruction was rising, powered by breakthroughs in afﬁne structure-from-motion [18], [19], [20] and the adoption of projective geometry [21].”
View-Invariant Analysis of Cyclic Motion (1997, methodology): “Therefore co-planarity of the feature set does not cause problems, in contrast to related techniques (Koenderink and Van Doorn, 1991; Tomasi and Kanade, 1992; Shapiroet al., 1994).”
Computer Vision — ECCV 2002 (2002, methodology): “Moreover, they cannot deal with changes of topology (with the exception of level set methods [3] and the approach presented in [12]).”
A Theory of Shape by Space Carving (1999, unknown): “The only requirements are that (1) the viewpoint of each photograph is known in a common 3D world reference frame (Euclidean, affine [18], or projective [19]), and (2) scene radiance follows a known, locally-computable radiance function.”
A Boolean map theory of visual attention. (2007, background): “Researchers have studied a number of phenomena that relate to the perception of structure, including global/local or Navon figures (large letters made out of small letters; Navon, 1977) and structure from motion (Koenderink & van Doorn, 1991).”
Vision Algorithms: Theory and Practice (2002, methodology): “In particular, the “Plane+Parallax” approach [14,11,13,7,9,8], which analyzes the parallax displacements of points relative to a (real or virtual) physical planar surface in the scene (the “reference plane”).”