Lidar Semantic Segmentation On Nuscenes

val mIoU

Results

Performance results of various models on this benchmark

Model Name	val mIoU	Paper Title	Repository
LSK3DNet	0.801	LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels
RangeFormer	-	Rethinking Range View Representation for LiDAR Segmentation	-
FRNet	0.790	FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation
SphereFormer	0.795	Spherical Transformer for LiDAR-based 3D Recognition
SPVCNN++	-	Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
2DPASS	-	2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds
WaffleIron	0.791	Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation
PMF-ResNet50	-	EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation
PTv2	0.802	Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
2D3DNet	-	Learning 3D Semantic Segmentation with only 2D Image Supervision	-
Open_world_incremental	-	-	-
OrangeNet	-	-	-
PTv3 + PPT	0.812	Point Transformer V3: Simpler, Faster, Stronger
SPVNAS	-	Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
Camera-LiDAR Fusion + HTC + Map	-	-	-
AF2S3Net	-	(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network	-
DITR	0.842	DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation
Vis-PolarNet	-	-	-
DB-Unet	-	-	-
CPFusion	-	-	-

0 of 35 row(s) selected.