Leonard Bruns

Leonard Bruns

I am a computer vision researcher working at Niantic Spatial and a PhD candidate at KTH.

My main research interests are at the intersection of 3D computer vision and robotics (and to a lesser degree computer graphics). I am particularly interested in the development of algorithms for robot perception such as pose and shape estimation of objects from partial information, dense SLAM, and visual relocalization.
Last updated: November 2, 2025
E-Mail | Twitter | Threads | LinkedIn | GitHub | Google Scholar | CV

Projects

ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training

Leonard Bruns, Axel Barroso-Laguna, Tommaso Cavallari, Áron Monszpart, Sowmya Munukutla, Victor Adrian Prisacariu, Eric Brachmann
IEEE/CVF International Conference on Computer Vision (ICCV), 26751-26761
pdf | arXiv | CVF | Project Page | Github

Neural Graph Map: Dense Mapping with Efficient Loop Closure Integration

Leonard Bruns, Jun Zhang, Patric Jensfelt
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2900-2909, 2025
pdf | arXiv | CVF | Project Page | Github

Transitional Grid Maps: Efficient Analytical Inference of Dynamic Environments under Limited Sensing

José Manuel Gaspar Sánchez, Leonard Bruns, Jana Tumova, Patric Jensfelt, Martin Törngren
IEEE Open Journal of Intelligent Transportation Systems 6, 1-10, 2025
arXiv | IEEE

Conditional Variational Autoencoders for Probabilistic Pose Regression

Fereidoon Zangeneh, Leonard Bruns, Amit Dekel, Alessandro Pieropan, Patric Jensfelt
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2794-2800, 2024
pdf | arXiv | IEEE

RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluation

Leonard Bruns, Patric Jensfelt
Robotics and Autonomous Systems 168, 2023
pdf | arXiv | Elsevier | Github

A Probabilistic Framework for Visual Localization in Ambiguous Scenes

Fereidoon Zangeneh, Leonard Bruns, Amit Dekel, Alessandro Pieropan, Patric Jensfelt
IEEE International Conference on Robotics and Automation (ICRA), 3969-3975, 2023
pdf | arXiv | IEEE | Github

SDF-Based RGB-D Camera Tracking in Neural Scene Representations

Leonard Bruns, Fereidoon Zangeneh, Patric Jensfelt
IEEE ICRA Workshop on Motion Planning with Implicit Neural Representations of Geometry, 2022
pdf | arXiv

SDFEst: Categorical Pose and Shape Estimation of Objects From RGB-D Using Signed Distance Fields

Leonard Bruns, Patric Jensfelt
IEEE Robotics and Automation Letters 7 (4), 9597-9604, 2022
pdf | arXiv | IEEE | Github

On the Evaluation of RGB-D-Based Categorical Pose and Shape Estimation

Leonard Bruns, Patric Jensfelt
Intelligent Autonomous Systems 17 (IAS-17), 360-377, 2023
pdf | arXiv | Springer | Github

Bench-MR: A Motion Planning Benchmark for Wheeled Mobile Robots

Eric Heiden*, Luigi Palmieri*, Leonard Bruns, Kai O. Arras, Gaurav S. Sukhatme, Sven Koenig
IEEE Robotics and Automation Letters 6 (3), 4536-4543, 2021
IEEE | Github

Dispertio: Optimal Sampling For Safe Deterministic Motion Planning

Luigi Palmieri*, Leonard Bruns*, Michael Meurer, Kai Oliver Arras
IEEE Robotics and Automation Letters 5 (2), 362-368, 2019
pdf | arXiv | IEEE

Deterministic Sampling-Based Motion Planning

Leonard Bruns
Master's Thesis, 2019
pdf