Fredrik Kahl

20

Papers

25

Total Citations

Papers (20)

Steerers: A Framework for Rotation Equivariant Keypoint Descriptors

ProSub: Probabilistic Open-Set Semi-Supervised Learning with Subspace-Based Out-of-Distribution Detection

Learning Structure-from-Motion with Graph Attention Networks

Optimal Relative Pose With Unknown Correspondences

Minimizing the Maximal Rank

Globally Optimal Rigid Intensity Based Registration: A Fast Fourier Domain Approach

Rotation Averaging and Strong Duality

Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions

A Cross-Season Correspondence Dataset for Robust Semantic Segmentation

Global Optimality for Point Set Registration Using Semidefinite Programming

Back to the Feature: Learning Robust Camera Localization From Pixels To Pose

A Quasiconvex Formulation for Radial Cameras

How Privacy-Preserving Are Line Clouds? Recovering Scene Details From 3D Lines

ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds

Privacy-Preserving Representations Are Not Enough: Recovering Scene Content From Camera Poses

Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization

CrowdDriven: A New Challenging Dataset for Outdoor Visual Localization

ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networks

Uncalibrated Structure from Motion on a Sphere

Investigating how ReLU-networks encode symmetries