Robert Wille — accepted AI-conference papers

2025

CaRaFFusion: Improving 2D Semantic Segmentation With Camera-Radar Point Cloud Fusion and Zero-Shot Image Inpainting

Huawei Sun, Bora Kunter Sahin, Georg Stettinger, Maximilian Bernhard, Matthias Schubert, Robert Wille

RA-L 2025

Segmenting objects in an environment is a crucial task for autonomous driving and robotics, as it enables a better understanding of the surroundings of each agent. Although camera sensors provide rich visual details, they are vulnerable to adverse weather conditions. In contrast, radar sensors remai

Cited by 4 Source ↗Scholar ↗

2025

ELMAR: Enhancing LiDAR Detection with 4D Radar Motion Awareness and Cross-modal Uncertainty

Xiangyuan Peng, Miao Tang, Huawei Sun, Kay Bierzynski, Lorenzo Servadei, Robert Wille

IROS 2025

LiDAR and 4D radar are widely used in autonomous driving and robotics. While LiDAR provides rich spatial information, 4D radar offers velocity measurement and remains robust under adverse conditions. As a result, increasing studies have focused on the 4D radar-LiDAR fusion method to enhance the perc

Cited by 0 Source ↗Scholar ↗

2025

LiRCDepth: Lightweight Radar-Camera Depth Estimation via Knowledge Distillation and Uncertainty Guidance

Huawei Sun, Nastassia Vysotskaya, Tobias Sukianto, Hao Feng, Julius Ott, Xiangyuan Peng +2

ICASSP 2025accepted

Recently, radar-camera fusion algorithms have gained significant attention as radar sensors provide geometric information that complements the limitations of cameras. However, most existing radar-camera depth estimation algorithms focus solely on improving performance, often neglecting computational…

Cited by 0 Source ↗Scholar ↗

2025

MutualForce: Mutual-Aware Enhancement for 4D Radar-LiDAR 3D Object Detection

Xiangyuan Peng, Huawei Sun, Kay Bierzynski, Anton Fischbacher, Lorenzo Servadei, Robert Wille

ICASSP 2025accepted

Radar and LiDAR have been widely used in autonomous driving as LiDAR provides rich structure information, and radar demonstrates high robustness under adverse weather. Recent studies highlight the effectiveness of fusing radar and LiDAR point clouds. However, challenges remain due to the modality mi…

Cited by 0 Source ↗Scholar ↗

2024

CaFNet: A Confidence-Driven Framework for Radar Camera Depth Estimation

Huawei Sun, Hao Feng, Julius Ott, Lorenzo Servadei, Robert Wille

IROS 2024poster

Depth estimation is critical in autonomous driving for interpreting 3D scenes accurately. Recently, radar-camera depth estimation has become of sufficient interest due to the robustness and low-cost properties of radar. Thus, this paper introduces a two-stage, end-to-end trainable Confidence-aware F…

Cited by 4 Source ↗code ↗Scholar ↗

2023

MEET: A Monte Carlo Exploration-Exploitation Trade-Off for Buffer Sampling

Julius Ott, Lorenzo Servadei, Jose A. Arjona-Medina, Enrico Rinaldi, Gianfranco Mauro, Daniela Sanchez Lopera +4

ICASSP 2023accepted

Data selection is essential for any data-based optimization technique, such as Reinforcement Learning. State-of-the-art sampling strategies for the experience replay buffer improve the performance of the Reinforcement Learning agent. However, they do not incorporate uncertainty in the Q-Value estima…

Cited by 0 Source ↗Scholar ↗

2022

Label-Aware Ranked Loss for Robust People Counting Using Automotive In-Cabin Radar

Lorenzo Servadei, Huawei Sun, Julius Ott, Michael Stephan, Souvik Hazra, Thomas Stadelmayer +3

ICASSP 2022accepted

In this paper, we introduce the Label-Aware Ranked loss, a novel metric loss function. Compared to the state-of-the-art Deep Metric Learning losses, this function takes advantage of the ranked ordering of the labels in regression problems. To this end, we first show that the loss minimises when data…

Cited by 0 Source ↗Scholar ↗