10 papers
Descriptor: Distance-Annotated Traffic Perception Question Answering (DTPQA)
Nikos Theodoridis, Tim Brophy, Reenu Mohandas +4
The remarkable progress of Vision-Language Models (VLMs) on a variety of tasks has raised interest in their application to automated driving. However, for these models to be truste…
SuperQuadricOcc: Real-Time Self-Supervised Semantic Occupancy Estimation with Superquadric Volume Rendering
Seamie Hayes, Alexandre Boulch, Andrei Bursuc +4
Self-supervision for semantic occupancy estimation is appealing as it removes the labour-intensive manual annotation, thus allowing one to scale to larger autonomous driving datase…
Probing Visual Concepts in Lightweight Vision-Language Models for Automated Driving
Nikos Theodoridis, Reenu Mohandas, Ganesh Sistu +4
The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabiliti…
Evaluating Small Vision-Language Models on Distance-Dependent Traffic Perception
Nikos Theodoridis, Tim Brophy, Reenu Mohandas +4
Vision-Language Models (VLMs) are becoming increasingly powerful, demonstrating strong performance on a variety of tasks that require both visual and textual understanding. Their s…
FisheyeGaussianLift: BEV Feature Lifting for Surround-View Fisheye Camera Perception
Shubham Sonarghare, Prasad Deshpande, Ciaran Hogan +2
Accurate BEV semantic segmentation from fisheye imagery remains challenging due to extreme non-linear distortion, occlusion, and depth ambiguity inherent to wide-angle projections.…
Evaluating the Impact of Weather-Induced Sensor Occlusion on BEVFusion for 3D Object Detection
Sanjay Kumar, Tim Brophy, Eoin Martino Grua +3
Accurate 3D object detection is essential for automated vehicles to navigate safely in complex real-world environments. Bird's Eye View (BEV) representations, which project multi-s…