Lars Hammarstrand
YOU?
Author Swipe
View article: NeuRadar: Neural Radiance Fields for Automotive Radar Point Clouds
NeuRadar: Neural Radiance Fields for Automotive Radar Point Clouds Open
Radar is an important sensor for autonomous driving (AD) systems due to its robustness to adverse weather and different lighting conditions. Novel view synthesis using neural radiance fields (NeRFs) has recently received considerable atten…
View article: ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networks
ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networks Open
Out-of-distribution (OOD) detection in deep learning has traditionally been framed as a binary task, where samples are either classified as belonging to the known classes or marked as OOD, with little attention given to the semantic relati…
View article: GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving
GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving Open
Self-supervised pre-training based on next-token prediction has enabled large language models to capture the underlying structure of text, and has led to unprecedented performance on a large array of tasks when applied at scale. Similarly,…
View article: Exploring Semi-Supervised Learning for Online Mapping
Exploring Semi-Supervised Learning for Online Mapping Open
The ability to generate online maps using only onboard sensory information is crucial for enabling autonomous driving beyond well-mapped areas. Training models for this task -- predicting lane markers, road edges, and pedestrian crossings …
View article: ProSub: Probabilistic Open-Set Semi-Supervised Learning with Subspace-Based Out-of-Distribution Detection
ProSub: Probabilistic Open-Set Semi-Supervised Learning with Subspace-Based Out-of-Distribution Detection Open
In open-set semi-supervised learning (OSSL), we consider unlabeled datasets that may contain unknown classes. Existing OSSL methods often use the softmax confidence for classifying data as in-distribution (ID) or out-of-distribution (OOD).…
View article: Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gap
Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gap Open
Neural Radiance Fields (NeRFs) have emerged as promising tools for advancing autonomous driving (AD) research, offering scalable closed-loop simulation and data augmentation capabilities. However, to trust the results achieved in simulatio…
View article: Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It
Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It Open
The task of online mapping is to predict a local map using current sensor observations, e.g. from lidar and camera, without relying on a pre-built map. State-of-the-art methods are based on supervised learning and are trained predominantly…
View article: Improving Open-Set Semi-Supervised Learning with Self-Supervision
Improving Open-Set Semi-Supervised Learning with Self-Supervision Open
Open-set semi-supervised learning (OSSL) embodies a practical scenario within semi-supervised learning, wherein the unlabeled training set encompasses classes absent from the labeled set. Many existing OSSL methods assume that these out-of…
View article: DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision
DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision Open
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 training set, also use a sizable collection of unlabeled data for…
View article: Extended Object Tracking Using Sets Of Trajectories with a PHD Filter
Extended Object Tracking Using Sets Of Trajectories with a PHD Filter Open
PHD filtering is a common and effective multiple object tracking (MOT) algorithm used in scenarios where the number of objects and their states are unknown. In scenarios where each object can generate multiple measurements per scan, some P…
View article: Extended Object Tracking Using Sets Of Trajectories with a PHD Filter
Extended Object Tracking Using Sets Of Trajectories with a PHD Filter Open
PHD filtering is a common and effective multiple object tracking (MOT) algorithm used in scenarios where the number of objects and their states are unknown. In scenarios where each object can generate multiple measurements per scan, some P…
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: Using Image Sequences for Long-Term Visual Localization
Using Image Sequences for Long-Term Visual Localization Open
Estimating the pose of a camera in a known scene, i.e., visual localization, is a core task for applications such as self-driving cars. In many scenarios, image sequences are available and existing work on combining single-image localizati…
View article: Long-Term Visual Localization Revisited
Long-Term Visual Localization Revisited Open
Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds. Practical visual localization approaches need to be robust to a wide variety of viewing co…
View article: Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization
Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization Open
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 practice, for example, encountered in autonomous driving. In ord…
View article: Fine-Grained Segmentation Networks: Self-Supervised Segmentation for\n Improved Long-Term Visual Localization
Fine-Grained Segmentation Networks: Self-Supervised Segmentation for\n Improved Long-Term Visual Localization Open
Long-term visual localization is the problem of estimating the camera pose of\na given query image in a scene whose appearance changes over time. It is an\nimportant problem in practice, for example, encountered in autonomous driving.\nIn …
View article: A Cross-Season Correspondence Dataset for Robust Semantic Segmentation
A Cross-Season Correspondence Dataset for Robust Semantic Segmentation Open
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 segmentation. Enforcing label consistency across the matches make…
View article: Radar Communication for Combating Mutual Interference of FMCW Radars
Radar Communication for Combating Mutual Interference of FMCW Radars Open
Commercial automotive radars used today are based on frequency modulated continuous wave signals due to the simple and robust detection method and good accuracy. However, the increase in both the number of radars deployed per vehicle and t…
View article: Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions
Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions Open
Visual localization enables autonomous vehicles to navigate in their\nsurroundings and augmented reality applications to link virtual to real worlds.\nPractical visual localization approaches need to be robust to a wide variety of\nviewing…
View article: Long-Term Visual Localization Using Semantically Segmented Images
Long-Term Visual Localization Using Semantically Segmented Images Open
Robust cross-seasonal localization is one of the major challenges in long-term visual navigation of autonomous vehicles. In this paper, we exploit recent advances in semantic segmentation of images, i.e., where each pixel is assigned a lab…
View article: Poisson Multi-Bernoulli Mapping Using Gibbs Sampling
Poisson Multi-Bernoulli Mapping Using Gibbs Sampling Open
This paper addresses the mapping problem. Using a conjugate prior form, we derive the exact theoretical batch multiobject posterior density of the map given a set of measurements. The landmarks in the map are modeled as extended objects, a…
View article: Coordination of Cooperative Autonomous Vehicles: Toward safer and more efficient road transportation
Coordination of Cooperative Autonomous Vehicles: Toward safer and more efficient road transportation Open
While intelligent transportation systems come in many shapes and sizes, arguably the most transformational realization will be the autonomous vehicle. As such vehicles become commercially available in the coming years, first on dedicated r…
View article: Long-Range Road Geometry Estimation Using Moving Vehicles and Roadside Observations
Long-Range Road Geometry Estimation Using Moving Vehicles and Roadside Observations Open
This paper presents an algorithm for estimating the shape of the road ahead of a host vehicle equipped with the following onboard sensors: a camera, a radar and vehicle internal sensors. The aim is to accurately describe the road geometry …