253 citations · 268 across the 21 of their papers we have counts for
7 papers · 1 filter
MuM: Multi-View Masked Image Modeling for 3D Vision
David Nordström, Johan Edstedt, Fredrik Kahl +1
Self-supervised learning on images seeks to extract meaningful visual representations from unlabeled data. When scaled to large datasets, this paradigm has achieved state-of-the-ar…
RoMa v2: Harder Better Faster Denser Feature Matching
Johan Edstedt, David Nordström, Yushan Zhang +7
Dense feature matching aims to estimate all correspondences between two images of a 3D scene and has recently been established as the gold standard due to its high accuracy and rob…
Radially Distorted Homographies, Revisited
Mårten Wadenbäck, Marcus Valtonen Örnhag, Johan Edstedt
Homographies are among the most prevalent transformations occurring in geometric computer vision and projective geometry, and homography estimation is consequently a crucial step i…
Quick ViTs: Speeding up Vision Transformers through Equivariance
David Nordström, Johan Edstedt, Fredrik Kahl +1
Natural images exhibit strong geometric regularities: local structures, such as edges, corners, and textures, appear in many orientations and mirror configurations. Since Vision Tr…
Less Biased Noise Scale Estimation for Threshold-Robust RANSAC
Johan Edstedt
The gold-standard for robustly estimating relative pose through image matching is RANSAC. While RANSAC is powerful, it requires setting the inlier threshold that determines whether…
ColabSfM: Collaborative Structure-from-Motion by Point Cloud Registration
Johan Edstedt, André Mateus, Alberto Jaenal
Structure-from-Motion (SfM) is the task of estimating 3D structure and camera poses from images. We define Collaborative SfM (ColabSfM) as sharing distributed SfM reconstructions.…
DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection
Johan Edstedt, Georg Bökman, Mårten Wadenbäck +1
Keypoints are what enable Structure-from-Motion (SfM) systems to scale to thousands of images. However, designing a keypoint detection objective is a non-trivial task, as SfM is no…