3D Semantic Segmentation On Nuscenes

mIoU

Results

Performance results of various models on this benchmark

		Paper Title
PTv2	82.6%	Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
FRNet	82.5%	FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation
AF2S3Net	78.3%	(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network

0 of 3 row(s) selected.