Multiple view geometry

By Anders Heyden, Marc Pollefeys. 2005

1,275 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.

In 3D Vision & Pose

Citations in the corpus

Understanding Deep Features with Computer-Generated Imagery (2015, methodology): “We adapted the publicly-available OpenGL renderer from [3], which renders a textured CAD model with matte surfaces under ﬁxed lighting conﬁguration and allows the viewpoint to be speciﬁed by a 3 × 4 camera matrix [15].”
RealFusion 360° Reconstruction of Any Object from a Single Image (2023, background): “The problem of reconstructing photometry and geometry together has been dramatically revital-ized by the introduction of neural radiance fields (RFs).”
Massively Parallel Multiview Stereopsis by Surface Normal Diffusion (2015, background): “Finally, the modification comes at little extra cost: the mapping between any two images is a plane-induced homography [16], corresponding to a 3D matrix-vector multiplication, see Fig.”
A Framework for Robust Subspace Learning (2003, methodology): “Other multi-linear models include tensorial approaches to structure from motion (Hartley and Zisserman, 2000) or Independent Component Analysis (ICA) (Cardoso, 1996).”
VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator (2017, methodology): “In most cases, a visual-only system can bootstrap itself by derived initial values from relative motion methods, such as the eight-point [32] or five-point [33] algorithms, or estimating the homogeneous matrices.”
Modeling the World from Internet Photo Collections (2008, methodology): “1999) (with related sparse matrix techniques, Szeliski and Kang 1994) have made their way into computer vision and are now regarded as the gold standard for performing optimal 3D reconstruction from correspondences (Hartley and Zisserman 2004).”
Skeletal graphs for efficient structure from motion (2008, methodology): “The skeletal set is reconstructed with an incremental bundle adjustment technique [21], and the remaining images are added using pose estimation [11].”
iSAM2: Incremental smoothing and mapping using the Bayes tree (2012, background): “Smoothing is closely related to structure from motion (Hartley and Zisserman, 2000) and bundle adjustment (Triggs et al., 1999) in computer vision.”
Orientation in Manhattan: equiprojective classes and sequential estimation (2005, neutral): “In the multiview case, this requires finding correspondences between features [2], [3], [4].”
DeMoN: Depth and Motion Network for Learning Monocular Stereo (2016, background): “The underlying 3D geometry is a consolidated ﬁeld, which is well covered in textbooks [17, 10].”
3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial Constraints (2006, neutral): “…2 afﬁne regions is equivalent to a match between m triples of points, thus the machinery developed in the structure from motion (Faugeras et al., 2001; Hartley and Zisserman, 2000; Tomasi and Kanade, 1992) and pose estimation (Huttenlocher and Ullman, 1987; Lowe, 1987) literature can in principle…”
D-NeRF: Neural Radiance Fields for Dynamic Scenes (2020, background): “Most traditional approaches for rigid scenes consist on reconstructing the scene from multiple views with Structure-from-Motion [14] and bundle adjustment [41], while other approaches propose light-ﬁeld based photography [18].”
Camera calibration with one-dimensional objects (2002, background): “A recent overview of this area can be found in [11].”