3 accepted papers
Vision-based 3D semantic occupancy prediction is vital for autonomous driving, enabling unified modeling of static infrastructure and dynamic agents. Global occupancy maps serve as long-term memory priors, providing valuable historical context that enhances local perception. This is particularly imp…
Scene understanding via multi-modal large language models and scene forecasting with world models have advanced the development of autonomous driving. The former maps visual inputs to driving-specific outputs, neglecting spatial reasoning and world dynamics. The latter captures world dynamics, lacki…
"Online construction of open-ended language scenes is crucial for robotic applications, where open-vocabulary interactive scene understanding is required. Recently, neural implicit representation has provided a promising direction for online interactive mapping. However, implementing open-vocabulary…