Search Results for author:
Found 36 papers, 15 papers with code
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.
Back to the Feature: Learning Robust Camera Localization from Pixels to Pose
In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms.
Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization
In this paper, we propose a new neural network, the Fine-Grained Segmentation Network (FGSN), that can be used to provide image segmentations with a larger number of labels and can be trained in a self-supervised fashion.
A case for using rotation invariant features in state of the art feature matchers
The aim of this paper is to demonstrate that a state of the art feature matcher (LoFTR) can be made more robust to rotations by simply replacing the backbone CNN with a steerable CNN which is equivariant to translations and image rotations.
Single-Image Depth Prediction Makes Feature Matching Easier
Good local features improve the robustness of many 3D re-localization and multi-view reconstruction pipelines.
A Cross-Season Correspondence Dataset for Robust Semantic Segmentation
We show that adding the correspondences as extra supervision during training improves the segmentation performance of the convolutional neural network, making it more robust to seasonal changes and weather conditions.
How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines
To address the resulting potential privacy risks for user-generated content, it was recently proposed to lift point clouds to line clouds by replacing 3D points by randomly oriented 3D lines passing through these points.
Steerers: A framework for rotation equivariant keypoint descriptors
Image keypoint descriptions that are discriminative and matchable over large changes in viewpoint are vital for 3D reconstruction.
ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds
In this paper, we are concerned with rotation equivariance on 2D point cloud data.
DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision
Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increasingly popular.
Improving Open-Set Semi-Supervised Learning with Self-Supervision
Open-set semi-supervised learning (OSSL) embodies a practical scenario within semi-supervised learning, wherein the unlabeled training set encompasses classes absent from the labeled set.
Investigating how ReLU-networks encode symmetries
These experiments are not only of interest for understanding how group equivariance is encoded in ReLU-networks, but they also give a new perspective on Entezari et al.'s permutation conjecture as we find that it is typically easier to merge a network with a group-transformed version of itself than merging two different networks.
Privacy-Preserving Representations are not Enough -- Recovering Scene Content from Camera Poses
In this paper, we show that an attacker can learn about details of a scene without any access by simply querying a localization service.
Privacy-Preserving Representations Are Not Enough: Recovering Scene Content From Camera Poses
In this paper, we show that an attacker can learn about details of a scene without any access by simply querying a localization service.
A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials
It is empirically demonstrated that such learned potentials can improve segmentation accuracy and that certain label class interactions are indeed better modelled by a non-Gaussian potential.
Rotation Averaging and Strong Duality
In this paper we explore the role of duality principles within the problem of rotation averaging, a fundamental task in a wide range of computer vision applications.
Multiresolution Search of the Rigid Motion Space for Intensity Based Registration
Our results show that low resolution target values can tightly bound the high-resolution target function in natural images.
Minimal Solvers for Relative Pose with a Single Unknown Radial Distortion
In this paper, we study the problems of estimating relative pose between two cameras in the presence of radial distortion.
Semantic Match Consistency for Long-Term Visual Localization
Robust and accurate visual localization across large appearance variations due to changes in time of day, seasons, or changes of the environment is a challenging problem which is of importance to application areas such as navigation of autonomous robots.
Optimal Geometric Fitting under the Truncated L2-Norm
First, it is shown that for a large class of problems, the statistically more desirable truncated L 2 -norm can be optimized with the same complexity.
Accurate Localization and Pose Estimation for Large 3D Models
For one, it makes the correspondence problem very difficult and it is likely that there will be a significant rate of outliers to handle.
Fast and Reliable Two-View Translation Estimation
It has long been recognized that one of the fundamental difficulties in theestimation of two-view epipolar geometry is the capability of handling outliers.
Optimal Relative Pose With Unknown Correspondences
Previous work on estimating the epipolar geometry of two views relies on being able to reliably match feature points based on appearance.
Minimizing the Maximal Rank
In the latter case, matrices are divided into sub-matrices and the envelope is computed for each sub-block individually.
Globally Optimal Rigid Intensity Based Registration: A Fast Fourier Domain Approach
In this paper, we propose a dual algorithm in which the optimization is done in the Fourier domain, and multiple resolution levels are replaced by multiple frequency bands.
Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss
We show how modeling heteroscedastic uncertainty improves performance upon our baseline, and furthermore, how back-propagation can be done through the optimizer in order to train the pipeline end-to-end for additional accuracy.
Pose Proposal Critic: Robust Pose Refinement by Learning Reprojection Errors
In recent years, considerable progress has been made for the task of rigid object pose estimation from a single RGB-image, but achieving robustness to partial occlusions remains a challenging problem.
Ranked #5 on
6D Pose Estimation using RGB
on Occlusion LineMOD
Azimuthal Rotational Equivariance in Spherical CNNs
In this work, we analyze linear operators from $L^2(S^2) \rightarrow L^2(S^2)$ which are equivariant to azimuthal rotations, that is, rotations around the z-axis.
On the Tightness of Semidefinite Relaxations for Rotation Estimation
In studying the empirical performance we note that there are few failure cases reported in the literature, in particular for estimation problems with a single rotation, motivating us to gain further theoretical understanding.
A Quasiconvex Formulation for Radial Cameras
In this paper we study structure from motion problems for 1D radial cameras.
CrowdDriven: A New Challenging Dataset for Outdoor Visual Localization
Visual localization is the problem of estimating the position and orientation from which a given image (or a sequence of images) is taken in a known scene.
Rigidity Preserving Image Transformations and Equivariance in Perspective
We characterize the class of image plane transformations which realize rigid camera motions and call these transformations `rigidity preserving'.
In Search of Projectively Equivariant Networks
Equivariance of linear neural network layers is well studied.
Adjustable Visual Appearance for Generalizable Novel View Synthesis
We present a generalizable novel view synthesis method which enables modifying the visual appearance of an observed scene so rendered views match a target weather or lighting condition without any scene specific training or access to reference views at the target condition.
Learning Structure-from-Motion with Graph Attention Networks
In this paper we tackle the problem of learning Structure-from-Motion (SfM) through the use of graph attention networks.
TimePillars: Temporally-Recurrent 3D LiDAR Object Detection
Object detection applied to LiDAR point clouds is a relevant task in robotics, and particularly in autonomous driving.
