Semantic Segmentation on Stanford2D3D - RGBD

Metric: Pixel Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Pixel Accuracy▼	Extra Data	Paper	Date↕	Code
1	ShapeConv-101	82.7	No	ShapeConv: Shape-aware Convolutional Layer for I...	2021-08-24	Code
2	CMX (SegFormer-B4)	82.6	No	CMX: Cross-Modal Fusion for RGB-X Semantic Segme...	2022-03-09	Code
3	CMX (SegFormer-B2)	82.3	No	CMX: Cross-Modal Fusion for RGB-X Semantic Segme...	2022-03-09	Code
4	MMAF-Net-152	76.5	No	Multi-Modal Attention-based Fusion Model for Sem...	2019-12-25	-
5	Depth-aware CNN	65.4	No	Depth-aware CNN for RGB-D Segmentation	2018-03-19	Code

#1ShapeConv-101SOTA
82.7
Pixel Accuracy· 2021-08-24
ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation Code
#2CMX (SegFormer-B4)
82.6
Pixel Accuracy· 2022-03-09
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers Code
#3CMX (SegFormer-B2)
82.3
Pixel Accuracy· 2022-03-09
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers Code
#4MMAF-Net-152SOTA
76.5
Pixel Accuracy· 2019-12-25
Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images
#5Depth-aware CNNSOTA
65.4
Pixel Accuracy· 2018-03-19
Depth-aware CNN for RGB-D Segmentation Code