activity
20172022
most citedCNN-based Lidar Point Cloud De-Noising in Adverse Weather

218 citations · 218 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2022

On the calibration of underrepresented classes in LiDAR-based semantic segmentation

Mariella Dreissig, Florian Piewak, Joschka Boedecker

The calibration of deep learning-based perception models plays a crucial role in their reliability. Our work focuses on a class-wise evaluation of several model's confidence perfor…

cs.CV2019218 cited

CNN-based Lidar Point Cloud De-Noising in Adverse Weather

Robin Heinzler, Florian Piewak, Philipp Schindler +1

Lidar sensors are frequently used in environment perception for autonomous vehicles and mobile robotics to complement camera, radar, and ultrasonic sensors. Adverse weather conditi…

cs.CV2019

Analyzing the Cross-Sensor Portability of Neural Network Architectures for LiDAR-based Semantic Labeling

Florian Piewak, Peter Pinggera, Marius Zöllner

State-of-the-art approaches for the semantic labeling of LiDAR point clouds heavily rely on the use of deep Convolutional Neural Networks (CNNs). However, transferring network arch…

cs.CV2018

Improved Semantic Stixels via Multimodal Sensor Fusion

Florian Piewak, Peter Pinggera, Markus Enzweiler +2

This paper presents a compact and accurate representation of 3D scenes that are observed by a LiDAR sensor and a monocular camera. The proposed method is based on the well-establis…

cs.CV2018

Boosting LiDAR-based Semantic Labeling by Cross-Modal Training Data Generation

Florian Piewak, Peter Pinggera, Manuel Schäfer +6

Mobile robots and autonomous vehicles rely on multi-modal sensor setups to perceive and understand their surroundings. Aside from cameras, LiDAR sensors represent a central compone…

cs.CV2017

Fully Convolutional Neural Networks for Dynamic Object Detection in Grid Maps

Florian Piewak, Timo Rehfeld, Michael Weber +1

Grid maps are widely used in robotics to represent obstacles in the environment and differentiating dynamic objects from static infrastructure is essential for many practical appli…