4 papers
Sparse3DTrack: Monocular 3D Object Tracking Using Sparse Supervision
Nikhil Gosala, B. Ravi Kiran, Senthil Yogamani +1
Monocular 3D object tracking aims to estimate temporally consistent 3D object poses across video frames, enabling autonomous agents to reason about scene dynamics. However, existin…
Class-Incremental Motion Forecasting
Nicolas Schischka, Nikhil Gosala, B Ravi Kiran +2
Motion forecasting enables autonomous vehicles to anticipate scene evolution by predicting the future trajectories of dynamic agents. However, existing approaches typically assume…
CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation
Hariprasath Govindarajan, Maciej K. Wozniak, Marvin Klingner +3
Vision foundation models (VFMs) such as DINO have led to a paradigm shift in 2D camera-based perception towards extracting generalized features to support many downstream tasks. Re…
LetsMap: Unsupervised Representation Learning for Semantic BEV Mapping
Nikhil Gosala, Kürsat Petek, B Ravi Kiran +4
Semantic Bird's Eye View (BEV) maps offer a rich representation with strong occlusion reasoning for various decision making tasks in autonomous driving. However, most BEV mapping a…