2 papers
cs.CV2026
DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning
Weimin Liu, Qingkun Li, Jiyuan Qiu +2
Drivers' visual attention provides critical cues for anticipating latent hazards and directly shapes decision-making and control maneuvers, where its absence can compromise traffic…
cs.CV2026
GeoSurDepth: Harnessing Foundation Model for Spatial Geometry Consistency-Oriented Self-Supervised Surround-View Depth Estimation
Weimin Liu, Wenjun Wang, Joshua H. Meng
Accurate surround-view depth estimation provides a competitive alternative to laser-based sensors and is essential for 3D scene understanding in autonomous driving. While empirical…