HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

3D Semantic Segmentation On Scannet200

평가 지표

test mIoU
val mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
test mIoU
val mIoU
Paper TitleRepository
DITR44.941.2--
PPT+SparseUNet33.231.9Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
Pamba37.136.3Pamba: Enhancing Global Interaction in Point Clouds via State Space Model-
OctFormer32.532.6OctFormer: Octree-based Transformers for 3D Point Clouds
PonderV2 + SparseUNet34.632.3PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
OneFormer3D-30.1OneFormer3D: One Transformer for Unified Point Cloud Segmentation
OA-CNNs32.333.3OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
LSK3DNet-33.1LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels
CSC24.926.4Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
MinkUNet25.325.04D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
ODIN36.840.5ODIN: A Single Model for 2D and 3D Segmentation
Sonata + PTv3-36.8--
BFANet36.037.3--
PTv3 + PPT39.336.0Point Transformer V3: Simpler, Faster, Stronger
LGround27.228.8Language-Grounded Indoor 3D Semantic Segmentation in the Wild
PTv3 ArKitLabelmaker41.440.3ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding
0 of 16 row(s) selected.