Systems and Experiment Paper: Construction of Panoramic Image Mosaics with Global and Local Alignment

By Harry Shum, Richard Szeliski. International Journal of Computer Vision, 2000

428 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.

Homography-based 2D Visual Tracking and Servoing (2007, methodology): “We compared the ESM method with the constant Gauss Newton method (CGN) proposed in Baker and Matthews (2001) and with the varying Gauss Newton method (VGN) proposed in Shum and Szeliski (2000).”
Catadioptric Projective Geometry (2001, background): “Omnidirectional sensing can be realized also with a rotating camera ( Shum & Szeliski, 2000 ).”
The dual-bootstrap iterative closest point algorithm with application to retinal image registration (2003, methodology): “Like many other multi-image alignment techniques [66], [71], the algorithm in [14] uses constraints generated from pairwise registration to initialize an adjustment procedure that results in transformations between all pairs of images.”
Active Appearance Models Revisited (2004, methodology): “It can be composed with the current warp using Equation (18) and results in the forwards compositional algorithm [Baker and Matthews, 2003], also used in [Shum and Szeliski, 2000].”
Bundled camera paths for video stabilization (2013, background): “Local alignment [Shum and Szeliski 2000] or a dual-homography model [Gao et al. 2011] can reduce alignment error caused by parallax.”