5 papers
BeyondSight: Object Permanence for End-to-End Autonomous Driving
Sandro Papais, Letian Wang, Mudit Jain +2
Autonomous driving operates in partially observable environments where actors may become fully occluded by other vehicles or infrastructure. Most end-to-end driving systems implici…
SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection
Sandro Papais, Lezhou Feng, Charles Cossette +1
Vision Transformers (ViTs) enable strong multi-view 3D detection but are limited by high inference latency from dense token and query processing across multiple views and large 3D…
SCATR: Mitigating New Instance Suppression in LiDAR-based Tracking-by-Attention via Second Chance Assignment and Track Query Dropout
Brian Cheong, Letian Wang, Sandro Papais +1
LiDAR-based tracking-by-attention (TBA) frameworks inherently suffer from high false negative errors, leading to a significant performance gap compared to traditional LiDAR-based t…
Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and Perspectives
Letian Wang, Marc-Antoine Lavoie, Sandro Papais +13
Motion prediction, recently popularized as world models, refers to the anticipation of future agent states or scene evolution, which is rooted in human cognition, bridging percepti…
ForeSight: Multi-View Streaming Joint Object Detection and Trajectory Forecasting
Sandro Papais, Letian Wang, Brian Cheong +1
We introduce ForeSight, a novel joint detection and forecasting framework for vision-based 3D perception in autonomous vehicles. Traditional approaches treat detection and forecast…