31 citations · 32 across the 15 of their papers we have counts for
19 papers
FedCKA: Representation-Guided Layer Personalization for Federated 3D Perception Across Driving Domains
Jolle Verhoog, Ali Burak Ünal, Holger Caesar
Robust perception in intelligent vehicles demands 3D object detectors that remain dependable under domain shifts, such as changes in time of day, location, or weather. However, due…
Does the VGGT Family Need All Its Layers?
Fengyi Zhang, Holger Caesar, Xiangyu Sun +3
Which layers of a feed-forward geometry model are needed to preserve both camera poses and dense 3D structure? We study layer redundancy in VGGT, , and VGGT-: 3,018 pruned…
SplatLabel: Pseudo-Labelling through 4D Gaussian Splatting
Nitya Nanvani, Andras Palffy, Holger Caesar
While 2D Vision Foundation Models offer a pathway to automate 3D semantic pseudo-labelling, translating these priors into robust 3D representations typically requires complex heuri…
Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
Chun-Peng Chang, Shaoxiang Wang, Alain Pagani +2
Modern image encoders achieve high generalization by decoupling semantic meaning from resolution, an ability yet to be fully realized in the 3D domain. We investigate the failure o…
4DRC-OCC: Robust Semantic Occupancy Prediction Through Fusion of 4D Radar and Camera
David Ninfa, Andras Palffy, Holger Caesar
Autonomous driving requires robust perception across diverse environmental conditions, yet 3D semantic occupancy prediction remains challenging under adverse weather and lighting.…
GaussianCaR: Gaussian Splatting for Efficient Camera-Radar Fusion
Santiago Montiel-Marín, Miguel Antunes-García, Fabio Sánchez-García +3
Robust and accurate perception of dynamic objects and map elements is crucial for autonomous vehicles performing safe navigation in complex traffic scenarios. While vision-only met…
AsyncBEV: Cross-modal Flow Alignment in Asynchronous 3D Object Detection
Shiming Wang, Holger Caesar, Liangliang Nan +1
In autonomous driving, multi-modal perception tasks like 3D object detection typically rely on well-synchronized sensors, both at training and inference. However, despite the use o…
4D-RaDiff: Latent Point Diffusion for 4D Radar Point Cloud Generation
Jimmie Kwok, Holger Caesar, Andras Palffy
Automotive radar has shown promising developments in environment perception due to its cost-effectiveness and robustness in adverse weather conditions. However, the limited availab…
ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimation
Simon Boeder, Fabian Gigengack, Simon Roesler +2
Recent progress in self- and weakly supervised occupancy estimation has largely relied on 2D projection or rendering-based supervision, which suffers from geometric inconsistencies…
Material-informed Gaussian Splatting for 3D World Reconstruction in a Digital Twin
Andy Huynh, João Malheiro Silva, Holger Caesar +1
3D reconstruction for Digital Twins often relies on LiDAR-based methods, which provide accurate geometry but lack the semantics and textures naturally captured by cameras. Traditio…
MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robots
Junseo Kim, Guido Dumont, Xinyu Gao +3
Dense 3D semantic occupancy perception is critical for mobile robots operating in pedestrian-rich environments, yet it remains underexplored compared to its application in autonomo…
BikeScenes: LiDAR Semantic Segmentation for Bicycles
Denniz Goren, Holger Caesar
The vulnerability of cyclists, exacerbated by the rising popularity of faster e-bikes, motivates adapting automotive perception technologies for bicycle safety. We use our multi-se…
Seeing Clearly, Forgetting Deeply: Revisiting Fine-Tuned Video Generators for Driving Simulation
Chun-Peng Chang, Chen-Yu Wang, Julian Schmidt +2
Recent advancements in video generation have substantially improved visual quality and temporal coherence, making these models increasingly appealing for applications such as auton…
ECCV 2024 W-CODA: 1st Workshop on Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving
Kai Chen, Ruiyuan Gao, Lanqing Hong +11
In this paper, we present details of the 1st W-CODA workshop, held in conjunction with the ECCV 2024. W-CODA aims to explore next-generation solutions for autonomous driving corner…
LeAP: Consistent multi-domain 3D labeling using Foundation Models
Simon Gebraad, Andras Palffy, Holger Caesar
Availability of datasets is a strong driver for research on 3D semantic understanding, and whilst obtaining unlabeled 3D point cloud data is straightforward, manually annotating th…
OSSA: Unsupervised One-Shot Style Adaptation
Robin Gerster, Holger Caesar, Matthias Rapp +2
Despite their success in various vision tasks, deep neural network architectures often underperform in out-of-distribution scenarios due to the difference between training and targ…
DPFT: Dual Perspective Fusion Transformer for Camera-Radar-based Object Detection
Felix Fent, Andras Palffy, Holger Caesar
The perception of autonomous vehicles has to be efficient, robust, and cost-effective. However, cameras are not robust against severe weather conditions, lidar sensors are expensiv…
Graph Convolutional Networks for Complex Traffic Scenario Classification
Tobias Hoek, Holger Caesar, Andreas Falkovén +1
A scenario-based testing approach can reduce the time required to obtain statistically significant evidence of the safety of Automated Driving Systems (ADS). Identifying these scen…
UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities
Shiming Wang, Holger Caesar, Liangliang Nan +1
Multi-sensor object detection is an active research topic in automated driving, but the robustness of such detection models against missing sensor input (modality missing), e.g., d…