253 citations · 268 across the 21 of their papers we have counts for
21 papers
Who Handles Orientation? Investigating Invariance in Feature Matching
David Nordström, Johan Edstedt, Fredrik Kahl +1
Finding matching keypoints between images is a core problem in 3D computer vision. However, modern matchers struggle with large in-plane rotations. A straightforward mitigation is…
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…
Affine steerers for structured keypoint description
Georg Bökman, Johan Edstedt, Michael Felsberg +1
We propose a way to train deep learning based keypoint descriptors that makes them approximately equivariant for locally affine transformations of the image plane. The main idea is…
From 2D to 3D: AISG-SLA Visual Localization Challenge
Jialin Gao, Bill Ong, Darld Lwi +13
Research in 3D mapping is crucial for smart city applications, yet the cost of acquiring 3D data often hinders progress. Visual localization, particularly monocular camera position…
DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector
Johan Edstedt, Georg Bökman, Zhenjun Zhao
In this paper, we analyze and improve into the recently proposed DeDoDe keypoint detector. We focus our analysis on some key issues. First, we find that DeDoDe keypoints tend to cl…
Steerers: A framework for rotation equivariant keypoint descriptors
Georg Bökman, Johan Edstedt, Michael Felsberg +1
Image keypoint descriptions that are discriminative and matchable over large changes in viewpoint are vital for 3D reconstruction. However, descriptions output by learned descripto…
Leveraging Cutting Edge Deep Learning Based Image Matching for Reconstructing a Large Scene from Sparse Images
Georg Bökman, Johan Edstedt
We present the top ranked solution for the AISG-SLA Visual Localisation Challenge benchmark (IJCAI 2023), where the task is to estimate relative motion between images taken in sequ…
Leveraging the Power of Data Augmentation for Transformer-based Tracking
Jie Zhao, Johan Edstedt, Michael Felsberg +2
Due to long-distance correlation and powerful pretrained models, transformer-based methods have initiated a breakthrough in visual object tracking performance. Previous works focus…
DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching
Johan Edstedt, Georg Bökman, Mårten Wadenbäck +1
Keypoint detection is a pivotal step in 3D reconstruction, whereby sets of (up to) K points are detected in each view of a scene. Crucially, the detected points need to be consiste…
GMSF: Global Matching Scene Flow
Yushan Zhang, Johan Edstedt, Bastian Wandt +3
We tackle the task of scene flow estimation from point clouds. Given a source and a target point cloud, the objective is to estimate a translation from each point in the source poi…
RoMa: Robust Dense Feature Matching
Johan Edstedt, Qiyu Sun, Georg Bökman +2
Feature matching is an important computer vision task that involves estimating correspondences between two images of a 3D scene, and dense methods estimate all such correspondences…
DKM: Dense Kernelized Feature Matching for Geometry Estimation
Johan Edstedt, Ioannis Athanasiadis, Mårten Wadenbäck +1
Feature matching is a challenging computer vision task that involves finding correspondences between two images of a 3D scene. In this paper we consider the dense approach instead…
Dense Gaussian Processes for Few-Shot Segmentation
Joakim Johnander, Johan Edstedt, Michael Felsberg +2
Few-shot segmentation is a challenging dense prediction task, which entails segmenting a novel query image given only a small annotated support set. The key problem is thus to desi…
VidHarm: A Clip Based Dataset for Harmful Content Detection
Johan Edstedt, Amanda Berg, Michael Felsberg +4
Automatically identifying harmful content in video is an important task with a wide range of applications. However, there is a lack of professionally labeled open datasets availabl…
Deep Gaussian Processes for Few-Shot Segmentation
Joakim Johnander, Johan Edstedt, Martin Danelljan +2
Few-shot segmentation is a challenging task, requiring the extraction of a generalizable representation from only a few annotated samples, in order to segment novel query images. A…