Benedikt Mersch — accepted AI-conference papers

2026

Radar Instance Transformer: Reliable Moving Instance Segmentation in Sparse Radar Point Clouds (Abstract Reprint)

Matthias Zeller, Vardeep Singh Sandhu, Benedikt Mersch, Jens Behley, Michael Heidingsfeld, Cyrill Stachniss

AAAI 2026technical

The perception of moving objects is crucial for autonomous robots performing collision avoidance in dynamic environments. LiDARs and cameras tremendously enhance scene interpretation but do not provide direct motion information and face limitations under adverse weather. Radar sensors overcome these

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

KISS-SLAM: A Simple, Robust, and Accurate 3D LiDAR SLAM System With Enhanced Generalization Capabilities

Tiziano Guadagnino, Benedikt Mersch, Saurabh Gupta, Ignacio Vizzo, Giorgio Grisetti, Cyrill Stachniss

IROS 2025

Robust and accurate localization and mapping of an environment using laser scanners, so-called LiDAR SLAM, is essential to many robotic applications. Early 3D LiDAR SLAM methods often exploited additional information from IMU or GNSS sensors to enhance localization accuracy and mitigate drift. Later

Cited by 17 Source ↗Scholar ↗

2024

Effectively Detecting Loop Closures using Point Cloud Density Maps

Saurabh Gupta, Tiziano Guadagnino, Benedikt Mersch, Ignacio Vizzo, Cyrill Stachniss

ICRA 2024poster

The ability to detect loop closures plays an essential role in any SLAM system. Loop closures allow correcting the drifting pose estimates from a sensor odometry pipeline. In this paper, we address the problem of effectively detecting loop closures in LiDAR SLAM systems in various environments with…

Cited by 15 Source ↗Scholar ↗

2024

Generalizable Stable Points Segmentation for 3D LiDAR Scan-to-Map Long-Term Localization

Ibrahim Hroob, Benedikt Mersch, Cyrill Stachniss, Marc Hanheide

RA-L 2024

Mobile robots increasingly operate in real-world environments that are subject to change over time. Accurate and robust localization is, however, crucial for the effective operation of autonomous mobile systems. In this letter, we tackle the challenge of developing a generalizable learned filter for

Cited by 4 Source ↗Scholar ↗

2024

HeLiMOS: A Dataset for Moving Object Segmentation in 3D Point Clouds From Heterogeneous LiDAR Sensors

Hyungtae Lim, Seoyeon Jang, Benedikt Mersch, Jens Behley, Hyun Myung, Cyrill Stachniss

IROS 2024

Moving object segmentation (MOS) using a 3D light detection and ranging (LiDAR) sensor is crucial for scene understanding and identification of moving objects. Despite the availability of various types of 3D LiDAR sensors in the market, MOS research still predominantly focuses on 3D point clouds fro

Cited by 13 Source ↗Scholar ↗

2024

Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion

Lucas Nunes, Rodrigo Marcuzzi, Benedikt Mersch, Jens Behley, Cyrill Stachniss

CVPR 2024poster

Computer vision techniques play a central role in the perception stack of autonomous vehicles. Such methods are employed to perceive the vehicle surroundings given sensor data. 3D LiDAR sensors are commonly used to collect sparse 3D point clouds from the scene. However compared to human perception s…

Cited by 21 Source ↗PDF ↗code ↗Scholar ↗

2023

Building Volumetric Beliefs for Dynamic Environments Exploiting Map-Based Moving Object Segmentation

Benedikt Mersch, Tiziano Guadagnino, Xieyuanli Chen, Ignacio Vizzo, Jens Behley, Cyrill Stachniss

RA-L 2023

Mobile robots that navigate in unknown environments need to be constantly aware of the dynamic objects in their surroundings for mapping, localization, and planning. It is key to reason about moving objects in the current observation and at the same time to also update the internal model of the stat

Cited by 48 Source ↗code ↗Scholar ↗

2023

ERASOR2: Instance-Aware Robust 3D Mapping of the Static World in Dynamic Scenes

Hyungtae Lim, Lucas Nunes, Benedikt Mersch, Xieyuanli Chen, Jens Behley, Hyun Myung +1

RSS 2023poster

A map of the environment is an essential component for robotic navigation. In the majority of cases, a map of the static part of the world is the basis for localization, planning, and navigation. However, dynamic objects that are presented in the scenes during mapping leave undesirable traces in the…

Cited by 28 Source ↗PDF ↗code ↗Scholar ↗

2023

KISS-ICP: In Defense of Point-to-Point ICP - Simple, Accurate, and Robust Registration If Done the Right Way

Ignacio Vizzo, Tiziano Guadagnino, Benedikt Mersch, Louis Wiesmann, Jens Behley, Cyrill Stachniss

RA-L 2023

Robust and accurate pose estimation of a robotic platform, so-called sensor-based odometry, is an essential part of many robotic applications. While many sensor odometry systems made progress by adding more complexity to the ego-motion estimation process, we move in the opposite direction. By removi

Cited by 494 Source ↗Scholar ↗

2023

Radar Velocity Transformer: Single-scan Moving Object Segmentation in Noisy Radar Point Clouds

Matthias Zeller, Vardeep S. Sandhu, Benedikt Mersch, Jens Behley, Michael Heidingsfeld, Cyrill Stachniss

ICRA 2023poster

The awareness about moving objects in the surroundings of a self-driving vehicle is essential for safe and reliable autonomous navigation. The interpretation of LiDAR and camera data achieves exceptional results but typically requires to accumulate and process temporal sequences of data in order to…

Cited by 9 Source ↗Scholar ↗

2022

Automatic Labeling to Generate Training Data for Online LiDAR-Based Moving Object Segmentation

Xieyuanli Chen, Benedikt Mersch, Lucas Nunes, Rodrigo Marcuzzi, Ignacio Vizzo, Jens Behley +1

RA-L 2022

Understanding the scene is key for autonomously navigating vehicles, and the ability to segment the surroundings online into moving and non-moving objects is a central ingredient of this task. Often, deep learning-based methods are used to perform moving object segmentation (MOS). The performance of

Cited by 95 Source ↗Scholar ↗

2022

Make it Dense: Self-Supervised Geometric Scan Completion of Sparse 3D LiDAR Scans in Large Outdoor Environments

Ignacio Vizzo, Benedikt Mersch, Rodrigo Marcuzzi, Louis Wiesmann, Jens Behley, Cyrill Stachniss

RA-L 2022

Mapping systems that turn sensor data into a model of the environment are standard components in mobile robotics. Outdoor robots are often equipped with 3D LiDAR sensors to obtain accurate range measurements at a high frame rate. The price for a robotic LiDAR sensor scales roughly linearly with the

Cited by 27 Source ↗Scholar ↗

2022

Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions

Benedikt Mersch, Xieyuanli Chen, Ignacio Vizzo, Lucas Nunes, Jens Behley, Cyrill Stachniss

RA-L 2022

A key challenge for autonomous vehicles is to navigate in unseen dynamic environments. Separating moving objects from static ones is essential for navigation, pose estimation, and understanding how other traffic participants are likely to move in the near future. In this work, we tackle the problem

Cited by 105 Source ↗code ↗Scholar ↗

2021

Embedded Stochastic Field Exploration with Micro Diving Agents using Bayesian Optimization-Guided Tree-Search and GMRFs

Daniel A Duecker, Benedikt Mersch, Rene C Hochdahl, Edwin Kreuzer

IROS 2021poster

Exploration and monitoring of hazardous fields in marine environments is one of the most promising tasks to be performed by fleets of low-cost micro autonomous underwater vehicles (μAUVs). In contrast to vehicles in other domains, underwater robots are forced to perform all computations onboard as n…

Cited by 9 Source ↗Scholar ↗

2021

Maneuver-based Trajectory Prediction for Self-driving Cars Using Spatio-temporal Convolutional Networks

Benedikt Mersch, Thomas Höllen, Kun Zhao, Cyrill Stachniss, Ribana Roscher

IROS 2021poster

The ability to predict the future movements of other vehicles is a subconscious and effortless skill for humans and key to safe autonomous driving. Therefore, trajectory prediction for autonomous cars has gained a lot of attention in recent years. It is, however, still a hard task to achieve human-l…

Cited by 50 Source ↗Scholar ↗

2021

Moving Object Segmentation in 3D LiDAR Data: A Learning-Based Approach Exploiting Sequential Data

Xieyuanli Chen, Shijie Li, Benedikt Mersch, Louis Wiesmann, Jürgen Gall, Jens Behley +1

RA-L 2021

The ability to detect and segment moving objects in a scene is essential for building consistent maps, making future state predictions, avoiding collisions, and planning. In this letter, we address the problem of moving object segmentation from 3D LiDAR scans. We propose a novel approach that pushes

Cited by 228 Source ↗code ↗Scholar ↗

2021

Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks

Benedikt Mersch, Xieyuanli Chen, Jens Behley, Cyrill Stachniss

CoRL 2021poster

Exploiting past 3D LiDAR scans to predict future point clouds is a promising method for autonomous mobile systems to realize foresighted state estimation, collision avoidance, and planning. In this paper, we address the problem of predicting future 3D LiDAR point clouds given a sequence of past LiDA…

Cited by 64 Source ↗code ↗Scholar ↗