Viktor Larsson
YOU?
Author Swipe
View article: Sparse Multiview Open-Vocabulary 3D Detection
Sparse Multiview Open-Vocabulary 3D Detection Open
The ability to interpret and comprehend a 3D scene is essential for many vision and robotics systems. In numerous applications, this involves 3D object detection, i.e.~identifying the location and dimensions of objects belonging to a speci…
View article: Dense Match Summarization for Faster Two-view Estimation
Dense Match Summarization for Faster Two-view Estimation Open
In this paper, we speed up robust two-view relative pose from dense correspondences. Previous work has shown that dense matchers can significantly improve both accuracy and robustness in the resulting pose. However, the large number of mat…
View article: Fixing the RANSAC Stopping Criterion
Fixing the RANSAC Stopping Criterion Open
For several decades, RANSAC has been one of the most commonly used robust estimation algorithms for many problems in computer vision and related fields. The main contribution of this paper lies in addressing a long-standing error baked int…
View article: Relative Pose Estimation through Affine Corrections of Monocular Depth Priors
Relative Pose Estimation through Affine Corrections of Monocular Depth Priors Open
Monocular depth estimation (MDE) models have undergone significant advancements over recent years. Many MDE models aim to predict affine-invariant relative depth from monocular images, while recent developments in large-scale training and …
View article: Single-Source Localization as an Eigenvalue Problem
Single-Source Localization as an Eigenvalue Problem Open
This paper introduces a novel method for solving the single-source localization problem, specifically addressing the case of trilateration. We formulate the problem as a weighted least-squares problem in the squared distances and demonstra…
View article: Robust Incremental Structure-from-Motion with Hybrid Features
Robust Incremental Structure-from-Motion with Hybrid Features Open
Structure-from-Motion (SfM) has become a ubiquitous tool for camera calibration and scene reconstruction with many downstream applications in computer vision and beyond. While the state-of-the-art SfM pipelines have reached a high level of…
View article: Revisiting Sampson Approximations for Geometric Estimation Problems
Revisiting Sampson Approximations for Geometric Estimation Problems Open
Many problems in computer vision can be formulated as geometric estimation problems, i.e. given a collection of measurements (e.g. point correspondences) we wish to fit a model (e.g. an essential matrix) that agrees with our observations. …
View article: Consensus-Adaptive RANSAC
Consensus-Adaptive RANSAC Open
RANSAC and its variants are widely used for robust estimation, however, they commonly follow a greedy approach to finding the highest scoring model while ignoring other model hypotheses. In contrast, Iteratively Reweighted Least Squares (I…
View article: GlueStick: Robust Image Matching by Sticking Points and Lines Together
GlueStick: Robust Image Matching by Sticking Points and Lines Together Open
Line segments are powerful features complementary to points. They offer structural cues, robust to drastic viewpoint and illumination changes, and can be present even in texture-less areas. However, describing and matching them is more cha…
View article: 3D Line Mapping Revisited
3D Line Mapping Revisited Open
In contrast to sparse keypoints, a handful of line segments can concisely encode the high-level scene layout, as they often delineate the main structural elements. In addition to offering strong geometric cues, they are also omnipresent in…
View article: Revisiting Rotation Averaging: Uncertainties and Robust Losses
Revisiting Rotation Averaging: Uncertainties and Robust Losses Open
In this paper, we revisit the rotation averaging problem applied in global Structure-from-Motion pipelines. We argue that the main problem of current methods is the minimized cost function that is only weakly connected with the input data …
View article: NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM
NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM Open
Neural implicit representations have recently become popular in simultaneous localization and mapping (SLAM), especially in dense visual SLAM. However, previous works in this direction either rely on RGB-D sensors, or require a separate mo…
View article: Localizing Unsynchronized Sensors With Unknown Sources
Localizing Unsynchronized Sensors With Unknown Sources Open
We propose a method for sensor array self-localization using a set of sources at unknown locations. The sources produce signals whose times of arrival are registered at the sensors. We look at the general case where neither the emission ti…
View article: DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients
DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients Open
Line segments are ubiquitous in our human-made world and are increasingly used in vision tasks. They are complementary to feature points thanks to their spatial extent and the structural information they provide. Traditional line detectors…
View article: Computationally Efficient Approach for Preheating of Battery Electric Vehicles before Fast Charging in Cold Climates
Computationally Efficient Approach for Preheating of Battery Electric Vehicles before Fast Charging in Cold Climates Open
This paper investigates battery preheating before fast charging, for a battery electric vehicle (BEV) driving in a cold climate. To prevent the battery from performance degradation at low temperatures, a thermal management (TM) system has …
View article: LaMAR: Benchmarking Localization and Mapping for Augmented Reality
LaMAR: Benchmarking Localization and Mapping for Augmented Reality Open
Localization and mapping is the foundational technology for augmented reality (AR) that enables sharing and persistence of digital content in the real world. While significant progress has been made, researchers are still mostly driven by …
View article: Optimal Thermal Management and Charging of Battery Electric Vehicles over Long Trips
Optimal Thermal Management and Charging of Battery Electric Vehicles over Long Trips Open
This paper studies optimal thermal management and charging of a battery electric vehicle driving over long distance trips. The focus is on the potential benefits of including a heat pump in the thermal management system for waste heat reco…
View article: Partially calibrated semi-generalized pose from hybrid point correspondences
Partially calibrated semi-generalized pose from hybrid point correspondences Open
In this paper we study the problem of estimating the semi-generalized pose of a partially calibrated camera, i.e., the pose of a perspective camera with unknown focal length w.r.t. a generalized camera, from a hybrid set of 2D-2D and 2D-3D…
View article: Learning-Based Dimensionality Reduction for Computing Compact and Effective Local Feature Descriptors
Learning-Based Dimensionality Reduction for Computing Compact and Effective Local Feature Descriptors Open
A distinctive representation of image patches in form of features is a key component of many computer vision and robotics tasks, such as image matching, image retrieval, and visual localization. State-of-the-art descriptors, from hand-craf…
View article: Optimal Thermal Management, Charging, and Eco-driving of Battery Electric Vehicles
Optimal Thermal Management, Charging, and Eco-driving of Battery Electric Vehicles Open
This paper addresses optimal battery thermal management (BTM), charging, and eco-driving of a battery electric vehicle (BEV) with the goal of improving its grid-to-meter energy efficiency. Thus, an optimisation problem is formulated, aimin…
View article: NICE-SLAM: Neural Implicit Scalable Encoding for SLAM
NICE-SLAM: Neural Implicit Scalable Encoding for SLAM Open
Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Nevertheless, existing methods produce over-smoothed scene reconstruc…
View article: A Cross-Platform Mobile Application for Ambulance CPR during Cardiac Arrests
A Cross-Platform Mobile Application for Ambulance CPR during Cardiac Arrests Open
This paper describes the implementation of a crossplatform software application to aid ambulance paramedics during CPR (Cardio-Pulmonary Resuscitation). It must be able to work both on iOS and Android devices, which are the leading platfor…
View article: On the Tightness of Semidefinite Relaxations for Rotation Estimation
On the Tightness of Semidefinite Relaxations for Rotation Estimation Open
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 rotations? In studying the empirical performance, we note that …
View article: MBA-VO: Motion Blur Aware Visual Odometry
MBA-VO: Motion Blur Aware Visual Odometry Open
Motion blur is one of the major challenges remaining for visual odometry methods. In low-light conditions where longer exposure times are necessary, motion blur can appear even for relatively slow camera motions. In this paper we present a…
View article: Pixel-Perfect Structure-from-Motion with Featuremetric Refinement
Pixel-Perfect Structure-from-Motion with Featuremetric Refinement Open
Finding local features that are repeatable across multiple views is a cornerstone of sparse 3D reconstruction. The classical image matching paradigm detects keypoints per-image once and for all, which can yield poorly-localized features an…
View article: Back to the Feature: Learning Robust Camera Localization from Pixels to Pose
Back to the Feature: Learning Robust Camera Localization from Pixels to Pose Open
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, from an input image. This either fails to generalize to new …
View article: SOLD2: Self-supervised Occlusion-aware Line Description and Detection
SOLD2: Self-supervised Occlusion-aware Line Description and Detection Open
Compared to feature point detection and description, detecting and matching line segments offer additional challenges. Yet, line features represent a promising complement to points for multi-view tasks. Lines are indeed well-defined by the…
View article: Localizing Unsynchronized Sensors with Unknown Sources
Localizing Unsynchronized Sensors with Unknown Sources Open
We propose a method for sensor array self-localization using a set of sources at unknown locations. The sources produce signals whose times of arrival are registered at the sensors. We look at the general case where neither the emission ti…
View article: From two rolling shutters to one global shutter
From two rolling shutters to one global shutter Open
A scientific paper titled "From two rolling shutters to one global shutter" co-funded by the H2020 Research and Innovation Action ARtwin (GA: 856994)