Search Results for author:
Found 48 papers, 24 papers with code
Q-REG: End-to-End Trainable Point Cloud Registration with Surface Curvature
Point cloud registration has seen recent success with several learning-based methods that focus on correspondence matching and, as such, optimize only for this objective.
Handbook on Leveraging Lines for Two-View Relative Pose Estimation
We propose an approach for estimating the relative pose between calibrated image pairs by jointly exploiting points, lines, and their coincidences in a hybrid manner.
Volumetric Semantically Consistent 3D Panoptic Mapping
We introduce an online 2D-to-3D semantic instance mapping algorithm aimed at generating comprehensive, accurate, and efficient semantic 3D maps suitable for autonomous agents in unstructured environments.
Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction
We tackle the problem of estimating a Manhattan frame, i. e. three orthogonal vanishing points, and the unknown focal length of the camera, leveraging a prior vertical direction.
AffineGlue: Joint Matching and Robust Estimation
Moreover, we derive a new minimal solver for homography estimation, requiring only a single affine correspondence (AC) and a gravity prior.
Consensus-Adaptive RANSAC
The proposed attention mechanism and one-step transformer provide an adaptive behavior that enhances the performance of RANSAC, making it a more effective tool for robust estimation.
DGC-GNN: Descriptor-free Geometric-Color Graph Neural Network for 2D-3D Matching
Direct matching of 2D keypoints in an input image to a 3D point cloud of the scene without requiring visual descriptors has garnered increased interest due to its lower memory requirements, inherent privacy preservation, and reduced need for expensive 3D model maintenance compared to visual descriptor-based methods.
SGAligner : 3D Scene Alignment with Scene Graphs
We propose SGAligner, the first method for aligning pairs of 3D scene graphs that is robust to in-the-wild scenarios (ie, unknown overlap -- if any -- and changes in the environment).
Ranked #1 on
Point Cloud Registration
on 3RScan
Efficient solutions to the relative pose of three calibrated cameras from four points using virtual correspondences
Our solutions are based on the simple idea of generating one additional virtual point correspondence in two views by using the information from the locations of the four input correspondences in the three views.
Revisiting Rotation Averaging: Uncertainties and Robust Losses
In this paper, we revisit the rotation averaging problem applied in global Structure-from-Motion pipelines.
A Large Scale Homography Benchmark
We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D.
SGAligner: 3D Scene Alignment with Scene Graphs
We propose SGAligner, the first method for aligning pairs of 3D scene graphs that is robust to in-the-wild scenarios (i. e., unknown overlap - if any - and changes in the environment).
A Large-Scale Homography Benchmark
We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D.
Fast Globally Optimal Surface Normal Estimation from an Affine Correspondence
The proposed approach provides a new globally optimal solution for this over-determined problem and proves that it reduces to a linear system that can be solved extremely efficiently.
Guiding Local Feature Matching with Surface Curvature
We propose a new method, named curvature similarity extractor (CSE), for improving local feature matching across images.
Generalized Differentiable RANSAC
We propose $\nabla$-RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline.
DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients
Their learned counterparts are more repeatable and can handle challenging images, but at the cost of a lower accuracy and a bias towards wireframe lines.
NeFSAC: Neurally Filtered Minimal Samples
We tested NeFSAC on more than 100k image pairs from three publicly available real-world datasets and found that it leads to one order of magnitude speed-up, while often finding more accurate results than USAC alone.
Relative Pose from SIFT Features
This paper proposes the geometric relationship of epipolar geometry and orientation- and scale-covariant, e. g., SIFT, features.
Learning To Find Good Models in RANSAC
We propose the Model Quality Network, MQ-Net in short, for predicting the quality, e. g. the pose error of essential matrices, of models generated inside RANSAC.
Relative Pose From a Calibrated and an Uncalibrated Smartphone Image
In this paper, we propose a new minimal and a non-minimal solver for estimating the relative camera pose together with the unknown focal length of the second camera.
Adaptive Reordering Sampler with Neurally Guided MAGSAC
We propose a new sampler for robust estimators that always selects the sample with the highest probability of consisting only of inliers.
Space-Partitioning RANSAC
A new algorithm is proposed to accelerate RANSAC model quality calculations.
VSAC: Efficient and Accurate Estimator for H and F
Experiments on four standard datasets show that VSAC is significantly faster than all its predecessors and runs on average in 1-2 ms, on a CPU.
USACv20: robust essential, fundamental and homography matrix estimation
We review the most recent RANSAC-like hypothesize-and-verify robust estimators.
Finding Geometric Models by Clustering in the Consensus Space
Dominant instances are found via a RANSAC-like sampling and a consolidation process driven by a model quality function considering previously proposed instances.
Calibrated and Partially Calibrated Semi-Generalized Homographies
In this paper, we propose the first minimal solutions for estimating the semi-generalized homography given a perspective and a generalized camera.
Minimal Solutions for Panoramic Stitching Given Gravity Prior
When capturing panoramas, people tend to align their cameras with the vertical axis, i. e., the direction of gravity.
Globally Optimal Relative Pose Estimation with Gravity Prior
Smartphones, tablets and camera systems used, e. g., in cars and UAVs, are typically equipped with IMUs (inertial measurement units) that can measure the gravity vector accurately.
Efficient Initial Pose-graph Generation for Global SfM
We propose ways to speed up the initial pose-graph generation for global Structure-from-Motion algorithms.
Pose Estimation for Vehicle-mounted Cameras via Horizontal and Vertical Planes
For the first class of solvers, the sought plane is expected to be perpendicular to one of the camera axes.
Minimal Cases for Computing the Generalized Relative Pose using Affine Correspondences
We propose three novel solvers for estimating the relative pose of a multi-camera system from affine correspondences (ACs).
Relative Pose from Deep Learned Depth and a Single Affine Correspondence
We propose a new approach for combining deep-learned non-metric monocular depth with affine correspondences (ACs) to estimate the relative pose of two calibrated cameras from a single correspondence.
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.
EPOS: Estimating 6D Pose of Objects with Symmetries
A data-dependent number of corresponding 3D locations is selected per pixel, and poses of possibly multiple object instances are estimated using a robust and efficient variant of the PnP-RANSAC algorithm.
Least-squares Optimal Relative Planar Motion for Vehicle-mounted Cameras
A new closed-form solver is proposed minimizing the algebraic error optimally, in the least-squares sense, to estimate the relative planar motion of two calibrated cameras.
Relative planar motion for vehicle-mounted cameras from a single affine correspondence
A new minimal solver is proposed for the semi-calibrated case, i. e. the camera parameters are known except a common focal length.
MAGSAC++, a fast, reliable and accurate robust estimator
A new method for robust estimation, MAGSAC++, is proposed.
Homography from two orientation- and scale-covariant features
Two new general constraints are derived on the scales and rotations which can be used in any geometric model estimation tasks.
Progressive NAPSAC: sampling from gradually growing neighborhoods
We propose Progressive NAPSAC, P-NAPSAC in short, which merges the advantages of local and global sampling by drawing samples from gradually growing neighborhoods.
Progressive-X: Efficient, Anytime, Multi-Model Fitting Algorithm
The Progressive-X algorithm, Prog-X in short, is proposed for geometric multi-model fitting.
Optimal Multi-view Correction of Local Affine Frames
The technique requires the epipolar geometry to be pre-estimated between each image pair.
Recovering affine features from orientation- and scale-invariant ones
An approach is proposed for recovering affine correspondences (ACs) from orientation- and scale-invariant, e. g. SIFT, features.
MAGSAC: marginalizing sample consensus
A method called, sigma-consensus, is proposed to eliminate the need for a user-defined inlier-outlier threshold in RANSAC.
Five-point Fundamental Matrix Estimation for Uncalibrated Cameras
We aim at estimating the fundamental matrix in two views from five correspondences of rotation invariant features obtained by e. g.\ the SIFT detector.
A Minimal Solution for Two-view Focal-length Estimation using Two Affine Correspondences
To select the best one out of the remaining candidates, a root selection technique is proposed outperforming the recent ones especially in case of high-level noise.
Graph-Cut RANSAC
A novel method for robust estimation, called Graph-Cut RANSAC, GC-RANSAC in short, is introduced.
Multi-Class Model Fitting by Energy Minimization and Mode-Seeking
The move replaces a set of labels with the corresponding density mode in the model parameter domain, thus achieving fast and robust optimization.
