HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Robust 3D Semantic Segmentation On

Metrics

mean Corruption Error (mCE)

Results

Performance results of various models on this benchmark

Paper Title
SqueezeSeg (64x2048)164.87%SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud
SqueezeSegV2 (64x2048)152.45%SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
RangeNet-21 (64x2048)136.33%RangeNet++: Fast and Accurate LiDAR Semantic Segmentation
RangeNet-53 (64x2048)130.66%RangeNet++: Fast and Accurate LiDAR Semantic Segmentation
PolarNet118.56%PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
SalsaNext (64x2048)116.14%SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving
FIDNet (64x2048)113.81%FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding
RPVNet111.74%RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation
WaffleIron109.54%Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation
GFNet108.68%GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation
CPGNet107.34%CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation
2DPASS106.14%2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds
PIDS-1.2x104.13%PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud
CENet (64x2048)103.41%CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving
Cylinder3D (spconv)103.25%Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
Cylinder3D (torchsparse)103.13%Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
PIDS-2.0x101.20%PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud
MinkUNet-34100.61%4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
SPVCNN-18100.30%Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
MinkUNet-18100.00%4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
0 of 22 row(s) selected.
Robust 3D Semantic Segmentation On | SOTA | HyperAI