Author name: Jiayuan Du, Yiming Zhao, Zhenglong Guo, Yong Pan, Wenbo Hou, Zhihui Hao, Kun Zhan, Qijun Chen

arXiv:2511.22039v3 Announce Type: replace
Abstract: This paper introduces a novel architecture for trajectory-conditioned forecasting of future 3D scene occupancy. In contrast to methods that rely on variational autoencoders (VAEs) to generate discret…