Semantic Segmentation On Replica

mIoU

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	mIoU	Paper Title
CMX	17.0	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
OVSeg	20.7	Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP
LabelMaker	42.1	LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories
InternImage	38.4	InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Mask3D	22.6	Mask3D: Mask Transformer for 3D Semantic Instance Segmentation

0 of 5 row(s) selected.