3D Semantic Segmentation On Semantickitti

Metrics

test mIoU

Results

Performance results of various models on this benchmark

		Paper Title
LSK3DNet	75.6%	LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels
PPT+PTv3	75.5%	Point Transformer V3: Simpler, Faster, Stronger
UniSeg	75.2%	UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase
SphereFormer	74.8%	Spherical Transformer for LiDAR-based 3D Recognition
DITR	74.4%	DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation
FRNet	73.3%	FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation
RangeFormer	73.3%	Rethinking Range View Representation for LiDAR Segmentation
2DPASS	72.9%	2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds
PTv2	72.6%	Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
PVKD	71.2%	Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation
WaffleIron	70.8%	Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation
AF2S3Net	70.8%	(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network
Cylinder3D	68.9%	Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
SPVNAS	66.4%	Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
JS3C-Net	66.0%	Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion
GFNet	65.4%	GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation
TORNADONet-HiRes	63.1%	TORNADO-Net: mulTiview tOtal vaRiatioN semAntic segmentation with Diamond inceptiOn module
KPRNet	63.1%	KPRNet: Improving projection-based LiDAR semantic segmentation
NAPL	61.6%	Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation
Meta-RangeSeg	61.0%	Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation

0 of 46 row(s) selected.

Command Palette

3D Semantic Segmentation On Semantickitti

Metrics

Results