联合语义分割和深度估计的交通场景感知算法
范康,钟铭恩,谭佳威,詹泽辉,冯妍

Traffic scene perception algorithm with joint semantic segmentation and depth estimation
Kang FAN,Ming’en ZHONG,Jiawei TAN,Zehui ZHAN,Yan FENG
表 6 SDFormer与单任务算法的深度估计性能对比
Tab.6 Comparison of depth estimation performance between SDFormer and single-task algorithms
方法编码器RMSEARENp/106GFLOPs
Lap-DepthResNet-1014.5530.15473.4186.5
DepthFormerSwin-B4.3260.127151.3282.0
pixelFormerSwin-B4.2580.115146.1346.4
SDFormerSwin-B4.4850.132116.7247.5