65 citations · 87 across the 18 of their papers we have counts for
22 papers
Learning Structure-from-Motion with Graph Attention Networks
Lucas Brynte, José Pedro Iglesias, Carl Olsson +1
In this paper we tackle the problem of learning Structure-from-Motion (SfM) through the use of graph attention networks. SfM is a classic computer vision problem that is solved tho…
Adjustable Visual Appearance for Generalizable Novel View Synthesis
Josef Bengtson, David Nilsson, Che-Tsung Lin +2
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 condi…
Privacy-Preserving Representations are not Enough -- Recovering Scene Content from Camera Poses
Kunal Chelani, Torsten Sattler, Fredrik Kahl +1
Visual localization is the task of estimating the camera pose from which a given image was taken and is central to several 3D computer vision applications. With the rapid growth in…
Investigating how ReLU-networks encode symmetries
Georg Bökman, Fredrik Kahl
Many data symmetries can be described in terms of group equivariance and the most common way of encoding group equivariances in neural networks is by building linear layers that ar…
Improving Open-Set Semi-Supervised Learning with Self-Supervision
Erik Wallin, Lennart Svensson, Fredrik Kahl +1
Open-set semi-supervised learning (OSSL) embodies a practical scenario within semi-supervised learning, wherein the unlabeled training set encompasses classes absent from the label…
In Search of Projectively Equivariant Networks
Georg Bökman, Axel Flinth, Fredrik Kahl
Equivariance of linear neural network layers is well studied. In this work, we relax the equivariance condition to only be true in a projective sense. We propose a way to construct…
DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision
Erik Wallin, Lennart Svensson, Fredrik Kahl +1
Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increasingly popular. SSL is a family of methods, which in addition to a labeled traini…
A case for using rotation invariant features in state of the art feature matchers
Georg Bökman, Fredrik Kahl
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 C…
Rigidity Preserving Image Transformations and Equivariance in Perspective
Lucas Brynte, Georg Bökman, Axel Flinth +1
We characterize the class of image plane transformations which realize rigid camera motions and call these transformations `rigidity preserving'. In particular, 2D translations of…
CrowdDriven: A New Challenging Dataset for Outdoor Visual Localization
Ara Jafarzadeh, Manuel Lopez Antequera, Pau Gargallo +4
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. It is an important part…
Back to the Feature: Learning Robust Camera Localization from Pixels to Pose
Paul-Edouard Sarlin, Ajaykumar Unagar, Måns Larsson +8
Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple learning algorithms. Many regress precise geometric quantities, like poses or 3D points, f…
How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines
Kunal Chelani, Fredrik Kahl, Torsten Sattler
Visual localization is the problem of estimating the camera pose of a given image with respect to a known scene. Visual localization algorithms are a fundamental building block in…
On the Tightness of Semidefinite Relaxations for Rotation Estimation
Lucas Brynte, Viktor Larsson, José Pedro Iglesias +2
Why is it that semidefinite relaxations have been so successful in numerous applications in computer vision and robotics for solving non-convex optimization problems involving rota…
Single-Image Depth Prediction Makes Feature Matching Easier
Carl Toft, Daniyar Turmukhambetov, Torsten Sattler +2
Good local features improve the robustness of many 3D re-localization and multi-view reconstruction pipelines. The problem is that viewing angle and distance severely impact the re…
Pose Proposal Critic: Robust Pose Refinement by Learning Reprojection Errors
Lucas Brynte, Fredrik Kahl
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…
Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization
Måns Larsson, Erik Stenborg, Carl Toft +3
Long-term visual localization is the problem of estimating the camera pose of a given query image in a scene whose appearance changes over time. It is an important problem in pract…
Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss
Eskil Jörgensen, Christopher Zach, Fredrik Kahl
Three-dimensional object detection from a single view is a challenging task which, if performed with good accuracy, is an important enabler of low-cost mobile robot perception. Pre…
A Cross-Season Correspondence Dataset for Robust Semantic Segmentation
Måns Larsson, Erik Stenborg, Lars Hammarstrand +3
In this paper, we present a method to utilize 2D-2D point matches between images taken during different image conditions to train a convolutional neural network for semantic segmen…
Rotation Averaging and Strong Duality
Anders Eriksson, Carl Olsson, Fredrik Kahl +1
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. In its convent…
A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials
Måns Larsson, Anurag Arnab, Fredrik Kahl +2
Are we using the right potential functions in the Conditional Random Field models that are popular in the Vision community? Semantic segmentation and other pixel-level labelling ta…
Multiresolution Search of the Rigid Motion Space for Intensity Based Registration
Behrooz Nasihatkon, Fredrik Kahl
We study the relation between the target functions of low-resolution and high-resolution intensity-based registration for the class of rigid transformations. Our results show that…
A linear framework for region-based image segmentation and inpainting involving curvature penalization
Thomas Schoenemann, Fredrik Kahl, Simon Masnou +1
We present the first method to handle curvature regularity in region-based image segmentation and inpainting that is independent of initialization. To this end we start from a new…