Semantics-Guided Multimodal Masked Autoencoder Pretraining for 3D BEV Object Detection 文章

ArXiv CS.CV2026-05-26NEWSen作者: Prabuddhi Wariyapperuma, Rajitha de Silva, Marc Hanheide, Thomas Bohn\'e, Leonardo Guevara
机器人
查看原文 →
关系图谱

Semantics-Guided Multimodal Masked Autoencoder Pretraining for 3D BEV Object Detection · 相关技术

相关技术

camerasauxiliary point-wise LiDAR semantic decoder branchsemantics-guided LiDAR voxel masking3D bird's-eye view (BEV) object detectionLiDARsemantics-guided multimodal masked autoencoder frameworkmultimodal masked autoencoders