Readings in computer vision: issues, problems, principles, and paradigms

By M. Fischler, O. Firschein. 1987

How researchers see this paper

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

Progressive Growing of GANs for Improved Quality, Stability, and Variation (2017, methodology): “We propose to study this by considering the multi-scale statistical similarity between distributions of local image patches drawn from Laplacian pyramid (Burt & Adelson, 1987) representations of generated and target images, starting at a low-pass resolution of 16 × 16 pixels.”
Linear scale-space (1994, unknown): “( 1986 ) and Hummel ( 1986 , 1987 ) .”
Elements of style (2015, methodology): “To detect groups of adjacent patches that undergo similar transformations, we use a Hough transform based voting strategy [Ballard 1987; Mitra et al. 2006].”
4-points congruent sets for robust pairwise surface registration (2008, methodology): “…been extensive work on pattern matching to seek resemblance between point sets in 2D. Famous algorithms for this problem include Hough transform [Ballard 1987], RANSAC [Fischler and Bolles 1981], image based alignment [Huttenlocher and Ullman 1990], and geometric hashing [Wolfson and Rigoutsos…”
Semi-convolutional Operators for Instance Segmentation (2018, background): “(3) and (4) are reminiscent of well known detection methods in computer vision: Hough voting [13,5] and implicit shape model (ISM) [30].”
Multi-task low-rank affinity pursuit for image segmentation (2011, background): “Hence, it has been widely studied in computer vision [1, 3, 6, 7, 10, 12, 29, 30, 34, 35].”