collaborators

9 papers

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

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

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…

cs.CV2026

ForecastOcc: Vision-based Semantic Occupancy Forecasting

Riya Mohan, Juana Valeria Hurtado, Rohit Mohan +1

Autonomous driving requires forecasting both geometry and semantics over time to effectively reason about future environment states. Existing vision-based occupancy forecasting met…

cs.CV2025

Hyperspectral Adapter for Semantic Segmentation with Vision Foundation Models

Juana Valeria Hurtado, Rohit Mohan, Abhinav Valada

Hyperspectral imaging (HSI) captures spatial information along with dense spectral measurements across numerous narrow wavelength bands. This rich spectral content has the potentia…

cs.CV2025

Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learning

Rohit Mohan, Julia Hindel, Florian Drews +3

Autonomous vehicles that navigate in open-world environments may encounter previously unseen object classes. However, most existing LiDAR panoptic segmentation models rely on close…