A computer algorithm for reconstructing a scene from two projections

By H. C. Longuet-Higgins. 1981

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

The fundamental matrix: Theory, algorithms, and stability analysis (2004, methodology): “Even though it is true that, by taking them into account, the fundamental matrix can be shown to be equivalent to the essential matrix introduced by Longuet-Higgins (1981) , we believe and have shown, as well as others (Faugeras, 1992; Hartley, 1992; Faugeras et al., 1992; Shashua, 1993b; Luong, 19”
A Flexible Technique for Accurate Omnidirectional Camera Calibration and Structure from Motion (2006, methodology): “Then, several point matches were picked manually from both views of the object and the eight point algorithm [17] was applied.”
Subspace methods for recovering rigid motion I: Algorithm and implementation (2004, methodology): “This section reports simulation results that compare the performance of our 3D motion algorithm with the linear discrete-time E-matrix approach [ Longuet-Higgins 1981; Tsai and Huang 1984; Weng et al. 19891.”
Automatic 3D model acquisition and generation of new images from video sequences (1998, background): “Although the general framework for uncalibrated structure from motion has been in place for some time [6] [14] [17] only recently have general acquisition systems come near to becoming a reality.”
Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning (2018, methodology): “Such labels may be estimated automatically using Structure-from-Motion [32].”
DeepV2D: Video to Depth with Differentiable Structure from Motion (2018, background): “2 RELATED WORK Structure from Motion: Beginning with early systems designed for small image collections (Longuet-Higgins, 1981; Mohr et al., 1995), Structure from Motion (SfM) has improved dramatically in regards to robustness, accuracy, and scalability.”
Algebraic Functions For Recognition (1995, methodology): “This includes classical structure from motion methods for recovering rigid camera motion parameters and metric shape [36, 18, 35, 14, 15], and more recent methods for recovering non-metric structure, i.”
Global Motion Estimation from Point Matches (2012, background): “This, multiview Structure from Motion (SfM) problem [1], [2], is a fundamental and well studied problem in computer vision.”
Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction (2018, background): “, [24], the “gold-standard” for geometric ego-motion estimation to date is based on a batch bundle adjustment of pose and scene structure [35], or on online Visual SLAM technqiues [4]).”
Learning to Find Good Correspondences (2017, methodology): “We further use it to set the influence of each correspondence in a weighted reformulation of the eight-point algorithm [18].”
Homography-based 2D Visual Tracking and Servoing (2007, methodology): “The camera translation (up to a scale factor) and the camera rotation can be estimated through the Essential matrix ( Longuet-Higgins 1981 � Hartley 1992� Faugeras 1993).”
An efficient solution to the five-point relative pose problem (2004, methodology): “It was introduced to the computer vision community by [ 20 ] and defended in [13].”