ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction
ProOOD:基于原型的分布外3D占用预测
机构 * Hunan University(湖南大学) ; Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)
专题命中 BEV与占用 :occupancy(title,abstract);autonomous driving(abstract);分类 cs.RO、cs.CV、eess.IV
AI总结 本文提出ProOOD方法,通过原型引导的语义填充和尾部挖掘提升3D占用预测和分布外检测性能,实验表明其在多个数据集上均取得显著改进。
Comments Accepted to CVPR 2026. The source code is publicly available at https://github.com/7uHeng/ProOOD