5 papers
GHOST: Ground-projected Hypotheses from Observed Structure-from-Motion Trajectories
Tomasz Frelek, Rohan Patil, Akshar Tumu +1
We present a scalable self-supervised approach for segmenting feasible vehicle trajectories from monocular images for autonomous driving in complex urban environments. Leveraging l…
Referring Expressions as a Lens into Spatial Language Grounding in Vision-Language Models
Akshar Tumu, Varad Shinde, Parisa Kordjamshidi
Spatial Reasoning is an important component of human cognition and is an area in which the latest Vision-language models (VLMs) show signs of difficulty. The current analysis works…
Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Driving
Akshar Tumu, Henrik I. Christensen, Marcell Vazquez-Chanlatte +2
Lane-topology prediction is a critical component of safe and reliable autonomous navigation. An accurate understanding of the road environment aids this task. We observe that this…
SD++: Enhancing Standard Definition Maps by Incorporating Road Knowledge using LLMs
Hitvarth Diwanji, Jing-Yan Liao, Akshar Tumu +3
High-definition maps (HD maps) are detailed and informative maps capturing lane centerlines and road elements. Although very useful for autonomous driving, HD maps are costly to bu…
Exploring Spatial Language Grounding Through Referring Expressions
Akshar Tumu, Parisa Kordjamshidi
Spatial Reasoning is an important component of human cognition and is an area in which the latest Vision-language models (VLMs) show signs of difficulty. The current analysis works…