collaborators

12 papers

cs.CV2026

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…

cs.CV2026

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.…

cs.RO2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

4D-RaDiff: Latent 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…