Multiple View Geometry in Computer Vision

By Richard I. Hartley, Andrew Zisserman. 2001

2,756 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/339093c7ed71919ce59a7e78979a77abd25bad0c

How researchers see this paper

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

In Geology

In Ocean Engineering

Citations in the corpus

D-NeRF: Neural Radiance Fields for Dynamic Scenes (2020, positive): “Recent advances in the emerging field of neural rendering, which learn scene representations encoding both geometry and appearance [26, 23, 19, 50, 29, 35], have achieved results that largely surpass those of traditional Structurefrom-Motion [14, 41, 38], light-field photography [18] and image-based”
High-quality single-shot capture of facial geometry (2010, neutral): “Thus the sample size for the RANSAC sampling is one.”
Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model (2017, neutral): “An alternative solution to this problem is to make the assumption that the last element of h 3 , which is H 33 is equal to 1 [33].”
Square Root SAM: Simultaneous Localization and Mapping via Square Root Information Smoothing (2006, neutral): “Interestingly, these two cases form the basis of the standard partitioned inverse, or “Schur complement”, which is well known in structure from motion applications (Triggs et al. 2000; Hartley and Zisserman 2000) and also used in GraphSLAM (Thrun et al. 2005).”
CosyPose: Consistent multi-view multi-object 6D pose estimation (2020, positive): “To tackle these challenges, we take inspiration from robust patch matching strategies that have been used in the structure from motion (SfM) literature [34,35].”
Occupancy Anticipation for Efficient Exploration and Navigation (2020, neutral): “Navigation Classical approaches to visual navigation perform passive or active SLAM to reconstruct geometric point-clouds [71,23] or semantic maps [5,55], facilitated by loop closures or learned odometry [7,39,8].”
Learning task-oriented grasping for tool manipulation from simulated self-supervision (2018, positive): “The NMS algorithm goes through the ranked antipodal grasps, and removes grasps which have short Euclidean distances Fig.”
Review of Stereo Vision Algorithms: From Software to Hardware (2008, neutral): “Stereo vision is a flourishing field, attracting the attention of many researchers (Forsyth and Ponce 2002 ; Hartley and Zisserman 2004 ).”
SBA: A software package for generic sparse bundle adjustment (2009, neutral): “Matrix M , also known as the projection or camera matrix , is an arbitrary homogeneous 3 × 4 matrix having rank 3 and depending on 11 parameters [Hartley and Zisserman 2000].”
Event-Based Vision: A Survey (2019, neutral): “. These works follow the classical twostep stereo solution: ﬁrst solve the event correspondence problem across image planes (i.e., epipolar matching) and then triangulate the location of the 3D point [193]. The main challenge is ﬁnding correspondences between events; it is the computationally intens”