collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure

Mohamed Abdelsamad, Bin Yang, Michael Ulrich +4

3D object detection from LiDAR point clouds is a core problem in autonomous driving. Recent advances in self-supervised learning (SSL) enable scalable pretraining and transfers wel…

cs.CV2026

Streaming Gaussian Encoding for 4D Panoptic Occupancy Tracking

Maximilian Luz, Thomas Nürnberg, Yakov Miron +1

Camera-based 4D panoptic occupancy tracking (4D-POT) is a promising paradigm for holistic scene understanding from multi-view imagery, enabling joint reasoning about geometry, sema…

cs.CV2026

Hyp2Former: Hierarchy-Aware Hyperbolic Embeddings for Open-Set Panoptic Segmentation

Yao Lu, Rohit Mohan, Florian Drews +2

Recognizing unknown objects is crucial for safety-critical applications such as autonomous driving and robotics. Open-Set Panoptic Segmentation (OPS) aims to segment known thing an…

cs.CV2026

Leveraging Previous-Traversal Point Cloud Map Priors for Camera-Based 3D Object Detection and Tracking

Markus Käppeler, Özgün Çiçek, Yakov Miron +1

Camera-based 3D object detection and tracking are central to autonomous driving, yet precise 3D object localization remains fundamentally constrained by depth ambiguity when no exp…

cs.CV2026

Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking

Maximilian Luz, Rohit Mohan, Thomas Nürnberg +3

Capturing 4D spatiotemporal scene structure is crucial for the safe and reliable operation of robots in dynamic environments. However, existing approaches typically address only pa…

cs.CV2026

UP-Fuse: Uncertainty-guided LiDAR-Camera Fusion for 3D Panoptic Segmentation

Rohit Mohan, Florian Drews, Yakov Miron +2

LiDAR-camera fusion enhances 3D panoptic segmentation by leveraging camera images to complement sparse LiDAR scans, but it also introduces a critical failure mode. Under adverse co…