GraphGSOcc: Semantic-Geometric Graph Transformer with Dynamic-Static Decoupling for 3D Gaussian Splatting-based Occupancy Prediction
GraphGSOcc: 基于语义-几何图变换器的3D高斯散射体占用预测方法,采用动态-静态解耦
机构 * School of Intelligent Systems Engineering(智能系统工程学院) ; Sun Yat-sen University(中山大学)
专题命中 BEV与占用 :occupancy(title,abstract);autonomous driving(abstract);分类 cs.CV、cs.AI
AI总结 GraphGSOcc通过结合语义和几何图变换器,解耦动态-静态物体优化,提升3D高斯散射体占用预测的性能和效率。
Journal ref IEEE Transactions on Circuits and Systems for Video Technology 2026