Search Results for author: Cyrill Stachniss

Found 45 papers, 28 papers with code

3D LiDAR Mapping in Dynamic Environments Using a 4D Implicit Neural Representation

1 code implementation6 May 2024 Xingguang Zhong, Yue Pan, Cyrill Stachniss, Jens Behley

We propose a novel approach for building accurate maps of dynamic environments utilizing a sequence of LiDAR scans.

Autonomous Vehicles Decoder

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

1 code implementation20 Mar 2024 Lucas Nunes, Rodrigo Marcuzzi, Benedikt Mersch, Jens Behley, Cyrill Stachniss

Our experimental evaluation shows that our method can complete the scene given a single LiDAR scan as input, producing a scene with more details compared to state-of-the-art scene completion methods.

Autonomous Vehicles Denoising

STAIR: Semantic-Targeted Active Implicit Reconstruction

no code implementations17 Mar 2024 Liren Jin, Haofei Kuang, Yue Pan, Cyrill Stachniss, Marija Popović

The key components of our framework are a semantic implicit neural representation and a compatible planning utility function based on semantic rendering and uncertainty estimation, enabling adaptive view planning to target objects of interest.

Deep Reinforcement Learning with Dynamic Graphs for Adaptive Informative Path Planning

1 code implementation7 Feb 2024 Apoorva Vashisth, Julius Rückin, Federico Magistri, Cyrill Stachniss, Marija Popović

To address these issues, we propose a novel deep reinforcement learning approach for adaptively replanning robot paths to map targets of interest in unknown 3D environments.

reinforcement-learning valid

PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistency

1 code implementation17 Jan 2024 Yue Pan, Xingguang Zhong, Louis Wiesmann, Thorbjörn Posewsky, Jens Behley, Cyrill Stachniss

In this paper, we propose a SLAM system for building globally consistent maps, called PIN-SLAM, that is based on an elastic and compact point-based implicit neural map representation.

Incremental Learning Pose Estimation

BonnBeetClouds3D: A Dataset Towards Point Cloud-based Organ-level Phenotyping of Sugar Beet Plants under Field Conditions

no code implementations22 Dec 2023 Elias Marks, Jonas Bömer, Federico Magistri, Anurag Sah, Jens Behley, Cyrill Stachniss

Agricultural production is facing severe challenges in the next decades induced by climate change and the need for sustainability, reducing its impact on the environment.

Keypoint Detection Point Cloud Completion +1

Semi-Supervised Active Learning for Semantic Segmentation in Unknown Environments Using Informative Path Planning

1 code implementation7 Dec 2023 Julius Rückin, Federico Magistri, Cyrill Stachniss, Marija Popović

We propose a planning method for semi-supervised active learning of semantic segmentation that substantially reduces human labelling requirements compared to fully supervised approaches.

Active Learning Segmentation +1

Data-Centric Digital Agriculture: A Perspective

no code implementations6 Dec 2023 Ribana Roscher, Lukas Roth, Cyrill Stachniss, Achim Walter

In response to the increasing global demand for food, feed, fiber, and fuel, digital agriculture is rapidly evolving to meet these demands while reducing environmental impact.

Constructing Metric-Semantic Maps using Floor Plan Priors for Long-Term Indoor Localization

1 code implementation20 Mar 2023 Nicky Zimmerman, Matteo Sodano, Elias Marks, Jens Behley, Cyrill Stachniss

We exploit 3D object detections from monocular RGB frames for both, the object-based map construction, and for globally localizing in the constructed map.

3D Object Detection Indoor Localization +3

Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving

1 code implementation CVPR 2023 Lucas Nunes, Louis Wiesmann, Rodrigo Marcuzzi, Xieyuanli Chen, Jens Behley, Cyrill Stachniss

Especially in autonomous driving, point clouds are sparse, and objects appearance depends on its distance from the sensor, making it harder to acquire large amounts of labeled training data.

Autonomous Driving Panoptic Segmentation +2

Gaussian Radar Transformer for Semantic Segmentation in Noisy Radar Data

no code implementations7 Dec 2022 Matthias Zeller, Jens Behley, Michael Heidingsfeld, Cyrill Stachniss

Scene understanding is crucial for autonomous robots in dynamic environments for making future state predictions, avoiding collisions, and path planning.

Scene Understanding Segmentation +1

Fully On-board Low-Power Localization with Multizone Time-of-Flight Sensors on Nano-UAVs

1 code implementation25 Nov 2022 Hanna Müller, Nicky Zimmerman, Tommaso Polonelli, Michele Magno, Jens Behley, Cyrill Stachniss, Luca Benini

Experimental evaluation using a nano-UAV open platform demonstrated that the proposed solution is capable of localizing on a 31. 2m$\boldsymbol{^2}$ map with 0. 15m accuracy and an above 95% success rate.

Predicting Dense and Context-aware Cost Maps for Semantic Robot Navigation

no code implementations17 Oct 2022 Yash Goel, Narunas Vaskevicius, Luigi Palmieri, Nived Chebrolu, Cyrill Stachniss

The preliminary experiments suggest that the cost maps generated by our network are suitable for the MPC and can guide the agent to the semantic goal more efficiently than a baseline approach.

Continuous Control Robot Navigation

Robust Double-Encoder Network for RGB-D Panoptic Segmentation

1 code implementation6 Oct 2022 Matteo Sodano, Federico Magistri, Tiziano Guadagnino, Jens Behley, Cyrill Stachniss

We propose a novel encoder-decoder neural network that processes RGB and depth separately through two encoders.

Decoder Panoptic Segmentation +1

IR-MCL: Implicit Representation-Based Online Global Localization

1 code implementation6 Oct 2022 Haofei Kuang, Xieyuanli Chen, Tiziano Guadagnino, Nicky Zimmerman, Jens Behley, Cyrill Stachniss

The experiments suggest that the presented implicit representation is able to predict more accurate 2D LiDAR scans leading to an improved observation model for our particle filter-based localization.

Robot Navigation

Learning-Based Dimensionality Reduction for Computing Compact and Effective Local Feature Descriptors

1 code implementation27 Sep 2022 Hao Dong, Xieyuanli Chen, Mihai Dusmanu, Viktor Larsson, Marc Pollefeys, Cyrill Stachniss

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.

Dimensionality Reduction Image Retrieval +2

Online Pole Segmentation on Range Images for Long-term LiDAR Localization in Urban Environments

1 code implementation15 Aug 2022 Hao Dong, Xieyuanli Chen, Simo Särkkä, Cyrill Stachniss

We further use the extracted poles as pseudo labels to train a deep neural network for online range image-based pole segmentation.

Adaptive Path Planning for UAVs for Multi-Resolution Semantic Segmentation

no code implementations3 Mar 2022 Felix Stache, Jonas Westheider, Federico Magistri, Cyrill Stachniss, Marija Popović

Efficient data collection methods play a major role in helping us better understand the Earth and its ecosystems.

Semantic Segmentation

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

1 code implementation28 Sep 2021 Benedikt Mersch, Xieyuanli Chen, Jens Behley, Cyrill Stachniss

In this paper, we address the problem of predicting future 3D LiDAR point clouds given a sequence of past LiDAR scans.

Collision Avoidance Decoder

Adaptive Path Planning for UAV-based Multi-Resolution Semantic Segmentation

no code implementations4 Aug 2021 Felix Stache, Jonas Westheider, Federico Magistri, Marija Popović, Cyrill Stachniss

In this paper, we address the problem of adaptive path planning for accurate semantic segmentation of terrain using unmanned aerial vehicles (UAVs).

Segmentation Semantic Segmentation

4D Panoptic LiDAR Segmentation

1 code implementation CVPR 2021 Mehmet Aygün, Aljoša Ošep, Mark Weber, Maxim Maximov, Cyrill Stachniss, Jens Behley, Laura Leal-Taixé

In this paper, we propose 4D panoptic LiDAR segmentation to assign a semantic class and a temporally-consistent instance ID to a sequence of 3D points.

4D Panoptic Segmentation Benchmarking +4

Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platform

2 code implementations20 Aug 2020 Shijie Li, Xieyuanli Chen, Yun Liu, Dengxin Dai, Cyrill Stachniss, Juergen Gall

Real-time semantic segmentation of LiDAR data is crucial for autonomously driving vehicles, which are usually equipped with an embedded platform and have limited computational resources.

Autonomous Vehicles Real-Time 3D Semantic Segmentation +1

Beyond Photometric Consistency: Gradient-based Dissimilarity for Improving Visual Odometry and Stereo Matching

no code implementations8 Apr 2020 Jan Quenzel, Radu Alexandru Rosu, Thomas Läbe, Cyrill Stachniss, Sven Behnke

We integrate both into stereo estimation as well as visual odometry systems and show clear benefits for typical disparity and direct image registration tasks when using our proposed metric.

Image Registration Pose Estimation +2

A Benchmark for LiDAR-based Panoptic Segmentation based on KITTI

no code implementations4 Mar 2020 Jens Behley, Andres Milioto, Cyrill Stachniss

Panoptic segmentation is the recently introduced task that tackles semantic segmentation and instance segmentation jointly.

Instance Segmentation Panoptic Segmentation +1

ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals

1 code implementation6 May 2019 Emanuele Palazzolo, Jens Behley, Philipp Lottes, Philippe Giguère, Cyrill Stachniss

For localization and mapping, we employ an efficient direct tracking on the truncated signed distance function (TSDF) and leverage color information encoded in the TSDF to estimate the pose of the sensor.


Fully Convolutional Networks with Sequential Information for Robust Crop and Weed Detection in Precision Farming

no code implementations9 Jun 2018 Philipp Lottes, Jens Behley, Andres Milioto, Cyrill Stachniss

Exploiting the crop arrangement information that is observable from the image sequences enables our system to robustly estimate a pixel-wise labeling of the images into crop and weed, i. e., a semantic segmentation.

Classification General Classification +1

Real-time Semantic Segmentation of Crop and Weed for Precision Agriculture Robots Leveraging Background Knowledge in CNNs

1 code implementation20 Sep 2017 Andres Milioto, Philipp Lottes, Cyrill Stachniss

Precision farming robots, which target to reduce the amount of herbicides that need to be brought out in the fields, must have the ability to identify crops and weeds in real time to trigger weeding actions.

Real-Time Semantic Segmentation

A General Framework for Flexible Multi-Cue Photometric Point Cloud Registration

no code implementations13 Sep 2017 Bartolomeo Della Corte, Igor Bogoslavskyi, Cyrill Stachniss, Giorgio Grisetti

Our approach exploits the different cues in a natural and consistent way and the registration can be done at framerate for a typical range or imaging sensor.

C++ code Point Cloud Registration

Cannot find the paper you are looking for? You can Submit a new open access paper.