HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

3D Semantic Segmentation On Sensaturban

평가 지표

mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	mIoU	Paper Title	Repository
TangentConv	33.30	Tangent Convolutions for Dense Prediction in 3D
SPGraph	37.29	Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
LCPFormer	63.4	LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers
KPConv	57.58	KPConv: Flexible and Deformable Convolution for Point Clouds
SparseConv	42.66	3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
EyeNet	62.30	Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scene
SCF-Net	55.1	SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation
BEV-Seg3D-Net	61.7	Efficient Urban-scale Point Clouds Segmentation with BEV Projection

0 of 8 row(s) selected.