We tackle the problem of estimating a Manhattan frame, i.e. three orthog...
We propose AffineGlue, a method for joint two-view feature matching and
...
RANSAC and its variants are widely used for robust estimation, however, ...
Direct matching of 2D keypoints in an input image to a 3D point cloud of...
Building 3D scene graphs has recently emerged as a topic in scene
repres...
We study the challenging problem of estimating the relative pose of thre...
In this paper, we revisit the rotation averaging problem applied in glob...
We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000
...
Line segments are ubiquitous in our human-made world and are increasingl...
Since RANSAC, a great deal of research has been devoted to improving bot...
This paper proposes the geometric relationship of epipolar geometry and
...
We propose Deep MAGSAC++ combining the advantages of traditional and dee...
A new algorithm is proposed to accelerate RANSAC model quality calculati...
We present VSAC, a RANSAC-type robust estimator with a number of novelti...
We review the most recent RANSAC-like hypothesize-and-verify robust
esti...
We propose Progressive-X+, a new algorithm for finding an unknown number...
In this paper, we propose the first minimal solutions for estimating the...
When capturing panoramas, people tend to align their cameras with the
ve...
Smartphones, tablets and camera systems used, e.g., in cars and UAVs, ar...
We propose ways to speed up the initial pose-graph generation for global...
We propose two novel solvers for estimating the egomotion of a calibrate...
We propose four novel solvers for estimating the relative pose of a
mult...
We propose a new approach for combining deep-learned non-metric monocula...
Local features e.g. SIFT and its affine and learned variants provide
reg...
We present a new method for estimating the 6D pose of rigid objects with...
Two solvers are proposed for estimating the extrinsic camera parameters ...
A new closed-form solver is proposed minimizing the algebraic error
opti...
A new method for robust estimation, MAGSAC++, is proposed. It introduces...
This paper proposes a geometric interpretation of the angles and scales ...
We propose Progressive NAPSAC, P-NAPSAC in short, which merges the advan...
The Progressive-X algorithm, Prog-X in short, is proposed for geometric
...
The technique requires the epipolar geometry to be pre-estimated between...
An approach is proposed for recovering affine correspondences (ACs) from...
A method called sigma-consensus is proposed to eliminate the need for a
...
We aim at estimating the fundamental matrix in two views from five
corre...
A minimal solution using two affine correspondences is presented to esti...
A novel method for robust estimation, called Graph-Cut RANSAC, GC-RANSAC...
We propose a general formulation, called Multi-X, for multi-class
multi-...