Search Results for author:
Found 44 papers, 17 papers with code
D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions.
Ranked #8 on
Image Matching
on IMC PhotoTourism
Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions
Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds.
NetVLAD: CNN architecture for weakly supervised place recognition
We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph.
Ranked #3 on
Visual Place Recognition
on Mid-Atlantic Ridge
Neighbourhood Consensus Networks
Second, we demonstrate that the model can be trained effectively from weak supervision in the form of matching and non-matching image pairs without the need for costly manual annotation of point to point correspondences.
Ranked #2 on
Semantic correspondence
on PF-PASCAL
(PCK (weak) metric)
Learning to Solve Hard Minimal Problems
The hard minimal problems arise from relaxing the original geometric optimization problem into a minimal problem with many spurious solutions.
InLoc: Indoor Visual Localization with Dense Matching and View Synthesis
We seek to predict the 6 degree-of-freedom (6DoF) pose of a query photograph with respect to a large indoor 3D map.
Making Affine Correspondences Work in Camera Geometry Computation
The main advantage of such solvers is that their sample size is smaller, e. g., only two instead of four matches are required to estimate a homography.
Trifocal Relative Pose from Lines at Points and its Efficient Solution
We present a method for solving two minimal problems for relative camera pose estimation from three views, which are based on three view correspondences of i) three points and one line and the novel case of ii) three points and two lines through two of the points.
PLMP -- Point-Line Minimal Problems in Complete Multi-View Visibility
We present a complete classification of all minimal problems for generic arrangements of points and lines completely observed by calibrated perspective cameras.
Viewing Graph Solvability via Cycle Consistency
In structure-from-motion the viewing graph is a graph where vertices correspond to cameras and edges represent fundamental matrices.
Robust Motion Segmentation from Pairwise Matches
In this paper we address a classification problem that has not been considered before, namely motion segmentation given pairwise matches only.
D-InLoc++: Indoor Localization in Dynamic Environments
Lastly, we describe and improve the mistakes caused by gradient-based comparison between synthetic and query images and publish a new pipeline for simulation of environments with movable objects from the Matterport scans.
Optimizing Elimination Templates by Greedy Parameter Search
For the problem of refractive absolute pose estimation with unknown focal length, we have found a template that is 20 times smaller.
Automatic Solver Generator for Systems of Laurent Polynomial Equations
The important property of an elimination template is that it applies to all polynomial systems in the family.
Viewing Graph Solvability in Practice
We present an advance in understanding the projective Structure-from-Motion, focusing in particular on the viewing graph: such a graph has cameras as nodes and fundamental matrices as edges.
On the Two-View Geometry of Unsynchronized Cameras
We present new methods for simultaneously estimating camera geometry and time shift from video sequences from multiple unsynchronized cameras.
Beyond Gröbner Bases: Basis Selection for Minimal Solvers
In this paper we show how we can make polynomial solvers based on the action matrix method faster, by careful selection of the monomial bases.
A clever elimination strategy for efficient minimal solvers
We present a new insight into the systematic generation of minimal solvers in computer vision, which leads to smaller and faster solvers.
Distortion Varieties
The distortion varieties of a given projective variety are parametrized by duplicating coordinates and multiplying them with monomials.
Hand-Eye and Robot-World Calibration by Global Polynomial Optimization
We show that the method of convex linear matrix inequality (LMI) relaxations can be used to effectively solve these problems and to obtain globally optimal solutions.
Euclidean Upgrade from a Minimal Number of Segments
In this paper, we propose an algebraic approach to upgrade a projective reconstruction to a Euclidean one, and aim at computing the rectifying homography from a minimal number of 9 segments of known length.
Fast and Accurate Camera Covariance Computation for Large 3D Reconstruction
Estimating uncertainty of camera parameters computed in Structure from Motion (SfM) is an important tool for evaluating the quality of the reconstruction and guiding the reconstruction process.
Beyond Grobner Bases: Basis Selection for Minimal Solvers
In this paper we show how we can make polynomial solvers based on the action matrix method faster, by careful selection of the monomial bases.
Linear solution to the minimal absolute pose rolling shutter problem
Our best 6-point solver, based on the new alternation technique, shows an identical or even better performance than the state-of-the-art R6P solver and is two orders of magnitude faster.
Visual Place Recognition with Repetitive Structures
Even more importantly, they violate the feature independence assumed in the bag-of-visual-words representation which often leads to over-counting evidence and significant degradation of retrieval performance.
Learning and Calibrating Per-Location Classifiers for Visual Place Recognition
The aim of this work is to localize a query photograph by finding other images depicting the same place in a large geotagged image database.
Radial Distortion Homography
The importance of precise homography estimation is often underestimated even though it plays a crucial role in various vision applications such as plane or planarity detection, scene degeneracy tests, camera motion classification, image stitching, and many more.
24/7 Place Recognition by View Synthesis
We address the problem of large-scale visual place recognition for situations where the scene undergoes a major change in appearance, for example, due to illumination (day/night), change of seasons, aging, or structural modifications over time such as buildings built or destroyed.
R6P - Rolling Shutter Absolute Camera Pose
Therefore we can use the standard P3P algorithm to estimate camera orientation and to bring the camera rotation matrix close to the identity.
Rolling Shutter Absolute Pose Problem With Known Vertical Direction
We compare our R5Pup to the state of the art RS and perspective methods and demonstrate that it outperforms them when vertical direction is known in the range of accuracy available on modern mobile devices.
Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization?
3D structure-based methods employ 3D models of the scene to estimate the full 6DOF pose of a camera very accurately.
Efficient Solution to the Epipolar Geometry for Radially Distorted Cameras
In this paper, we present a new efficient solution to this problem that uses 10 image correspondences.
Is This The Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization
The pose with the largest geometric consistency with the query image, e. g., in the form of an inlier count, is then selected in a second stage.
PL${}_{1}$P -- Point-line Minimal Problems under Partial Visibility in Three Views
We present a complete classification of minimal problems for generic arrangements of points and lines in space observed partially by three calibrated perspective cameras when each line is incident to at most one point.
Minimal Rolling Shutter Absolute Pose with Unknown Focal Length and Radial Distortion
The internal geometry of most modern consumer cameras is not adequately described by the perspective projection.
From two rolling shutters to one global shutter
Most consumer cameras are equipped with electronic rolling shutter, leading to image distortions when the camera moves during image capture.
On the Usage of the Trifocal Tensor in Motion Segmentation
Motion segmentation, i. e., the problem of clustering data in multiple images based on different 3D motions, is an important task for reconstructing and understanding dynamic scenes.
PL₁P - Point-line Minimal Problems under Partial Visibility in Three Views
We present a complete classification of minimal problems for generic arrangements of points and lines in space observed partially by three calibrated perspective cameras when each line is incident to at most one point.
Galois/monodromy groups for decomposing minimal problems in 3D reconstruction
We consider three classical cases--3-point absolute pose, 5-point relative pose, and 4-point homography estimation for calibrated cameras--where the decomposition and symmetries may be naturally understood in terms of the Galois/monodromy group.
Reconstructing Small 3D Objects in front of a Textured Background
It is a particular variation of multibody structure from motion, which specializes to two objects only.
Objects Can Move: 3D Change Detection by Geometric Transformation Constistency
AR/VR applications and robots need to know when the scene has changed.
Four-View Geometry With Unknown Radial Distortion
The minimal case for reconstruction requires 13 points in 4 views for both the calibrated and uncalibrated cameras.
Order-One Rolling Shutter Cameras
We provide a unified theory for the important class of order-one rolling shutter (RS$_1$) cameras.
Socially Pertinent Robots in Gerontological Healthcare
Despite the many recent achievements in developing and deploying social robotics, there are still many underexplored environments and applications for which systematic evaluation of such systems by end-users is necessary.
