Semantic Segmentation on SUN-RGBD

Metric: Mean IoU (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	Mean IoU▼	Extra Data	Paper	Date↕	Code
1	GeminiFusion (Swin-Large)	54.6	No	GeminiFusion: Efficient Pixel-wise Multimodal Fu...	2024-06-03	Code
2	DiffusionMMS	54	No	Diffusion-based RGB-D Semantic Segmentation with...	2024-09-23	-
3	GeminiFusion (MiT-B5)	53.3	No	GeminiFusion: Efficient Pixel-wise Multimodal Fu...	2024-06-03	Code
4	DFormerv2-L	53.3	No	DFormerv2: Geometry Self-Attention for RGBD Sema...	2025-04-07	Code
5	GeminiFusion (MiT-B3)	52.7	No	GeminiFusion: Efficient Pixel-wise Multimodal Fu...	2024-06-03	Code
6	ICM	50.6	No	-	-	Code
7	CMX (B5)	48.17	Yes	Efficient RGB-D Semantic Segmentation for Indoor...	2020-11-13	Code
8	TokenFusion (S)	45.73	Yes	Self-Supervised Model Adaptation for Multimodal ...	2018-08-11	Code
9	DPLNet	38.4	Yes	Self-Supervised Model Adaptation for Multimodal ...	2018-08-11	Code
10	Index Network	33.48	No	Index Network	2019-08-11	Code
11	DeepLab-LargeFOV	32.08	No	Semantic Image Segmentation with Deep Convolutio...	2014-12-22	Code
12	SegNet	31.84	No	SegNet: A Deep Convolutional Encoder-Decoder Arc...	2015-11-02	Code
13	FCN	27.39	No	Fully Convolutional Networks for Semantic Segmen...	2016-05-20	Code

#1GeminiFusion (Swin-Large)SOTA
54.6
Mean IoU· 2024-06-03
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer Code
#2DiffusionMMS
54
Mean IoU· 2024-09-23
Diffusion-based RGB-D Semantic Segmentation with Deformable Attention Transformer
#3GeminiFusion (MiT-B5)
53.3
Mean IoU· 2024-06-03
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer Code
#4DFormerv2-L
53.3
Mean IoU· 2025-04-07
DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation Code
#5GeminiFusion (MiT-B3)
52.7
Mean IoU· 2024-06-03
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer Code
#6ICM
50.6
Mean IoU
No paperCode
#7CMX (B5)SOTA
48.17
Mean IoU· Extra Data· 2020-11-13
Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis Code
#8TokenFusion (S)SOTA
45.73
Mean IoU· Extra Data· 2018-08-11
Self-Supervised Model Adaptation for Multimodal Semantic Segmentation Code
#9DPLNet
38.4
Mean IoU· Extra Data· 2018-08-11
Self-Supervised Model Adaptation for Multimodal Semantic Segmentation Code
#10Index Network
33.48
Mean IoU· 2019-08-11
Index Network Code
#11DeepLab-LargeFOVSOTA
32.08
Mean IoU· 2014-12-22
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs Code
#12SegNet
31.84
Mean IoU· 2015-11-02
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation Code
#13FCN
27.39
Mean IoU· 2016-05-20
Fully Convolutional Networks for Semantic Segmentation Code