5 papers
EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence
Jiaxu Wan, Xu Wang, Mengwei Xie +6
Video-based spatial reasoning -- such as estimating distances, judging directions, or understanding layouts from multiple views -- requires selecting informative frames and, when n…
Online Navigation Refinement: Achieving Lane-Level Guidance by Associating Standard-Definition and Online Perception Maps
Jiaxu Wan, Xu Wang, Mengwei Xie +7
Lane-level navigation is critical for geographic information systems and navigation-based tasks, offering finer-grained guidance than road-level navigation by standard definition (…
AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction
Ruikai Li, Xinrun Li, Mengwei Xie +12
Online High-Definition (HD) map construction is pivotal for autonomous driving. While recent approaches leverage historical temporal fusion to improve performance, we identify a cr…
FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving
Shuang Zeng, Xinyuan Chang, Mengwei Xie +6
Vision-Language-Action (VLA) models offer significant potential for end-to-end driving, yet their reasoning is often constrained by textual Chains-of-Thought (CoT). This symbolic c…
SeqGrowGraph: Learning Lane Topology as a Chain of Graph Expansions
Mengwei Xie, Shuang Zeng, Xinyuan Chang +4
Accurate lane topology is essential for autonomous driving, yet traditional methods struggle to model the complex, non-linear structures-such as loops and bidirectional lanes-preva…