10-shot image generation on NYU Depth v2

Metric: Mean IoU (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

#	Model↕	Mean IoU▼	Extra Data	Paper	Date↕	Code
1	OmniVec2	63.6	Yes	-	-	-
2	DiffusionMMS (DAT++-S)	61.5	No	Diffusion-based RGB-D Semantic Segmentation with...	2024-09-23	-
3	DepthMatch (DINOv2-S)	61.4	Yes	DepthMatch: Semi-Supervised RGB-D Scene Parsing ...	2025-05-26	-
4	GeminiFusion (Swin-Large)	60.9	Yes	GeminiFusion: Efficient Pixel-wise Multimodal Fu...	2024-06-03	Code
5	OmniVec	60.8	Yes	OmniVec: Learning robust representations with cr...	2023-11-07	-
6	GeminiFusion (Swin-Large)	60.2	No	GeminiFusion: Efficient Pixel-wise Multimodal Fu...	2024-06-03	Code
7	DPLNet	59.3	No	Efficient Multimodal Semantic Segmentation via D...	2023-12-01	Code
8	EMSANet (2x ResNet-34 NBt1D, PanopticNDT version, finetuned)	59.02	No	PanopticNDT: Efficient and Robust Panoptic Mapping	2023-09-24	Code
9	GeminiFusion (MiT-B5)	57.7	No	GeminiFusion: Efficient Pixel-wise Multimodal Fu...	2024-06-03	Code
10	GeminiFusion (MiT-B3)	56.8	No	GeminiFusion: Efficient Pixel-wise Multimodal Fu...	2024-06-03	Code
11	HAPNet	55	No	HAPNet: Toward Superior RGB-Thermal Scene Parsin...	2024-04-04	Code
12	ICM	50.7	No	-	-	Code
13	ESANet (R34-NBt1D)	50.3	No	Efficient RGB-D Semantic Segmentation for Indoor...	2020-11-13	Code
14	MTI-Net (HRNet-48)	49	No	MTI-Net: Multi-Scale Task Interaction Networks f...	2020-01-19	Code
15	ESANet (R18-NBt1D )	48.17	No	Efficient RGB-D Semantic Segmentation for Indoor...	2020-11-13	Code
16	PGT (Swin-S)	46.43	No	Prompt Guided Transformer for Multi-Task Dense P...	2023-07-28	Code
17	VCD+DeepLab (VGG16)	45.3	No	-	-	-
18	TD2-PSP50	43.5	No	Temporally Distributed Networks for Fast Video S...	2020-04-03	Code
19	PGT (Swin-T)	41.61	No	Prompt Guided Transformer for Multi-Task Dense P...	2023-07-28	Code
20	TD4-PSP18	37.4	No	Temporally Distributed Networks for Fast Video S...	2020-04-03	Code