SPOT-Occ: Sparse Prototype-guided Transformer for Camera-based 3D Occupancy Prediction
SPOT-Occ: 基于稀疏原型的Transformer用于基于相机的3D占用预测
机构 * Artificial Intelligence Thrust, The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学人工智能方向(广州)) ; Department of Computer Science and Engineering, The Hong Kong University of Science and Technology(香港科学与技术大学计算机科学与工程系)
专题命中 BEV与占用 :occupancy(title,abstract);分类 cs.RO、cs.CV
AI总结 SPOT-Occ提出了一种基于稀疏原型的Transformer解码器,通过引导特征选择和聚焦聚合提升基于相机的3D占用预测的效率与精度。
Comments 8 pages, 6 figures