HyperAIHyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAIHyperAI초신경

Robust 3D Semantic Segmentation On Nuscenes C

평가 지표

mean Corruption Error (mCE)

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
mean Corruption Error (mCE)
Paper TitleRepository
SPVCNN-18106.65%Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution-
Cylinder3D (torchsparse)105.56%Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation-
SPVCNN-3497.45%Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution-
PolarNet115.09%PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation-
Cylinder3D (spconv)111.84%Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation-
MinkUNet-3496.37%4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks-
GFNet92.55%GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation-
WaffleIron106.73%Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation-
CENet112.79%CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving-
MinkUNet-18100.00%4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks-
FIDNet122.42%FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding-
2DPASS98.56%2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds-
0 of 12 row(s) selected.