Semantic Segmentation on Stanford2D3D - RGBD

12개 결과 · ⬇ CSV · JSON

mIoU

Rank	Model	mIoU	Pixel Accuracy	mAcc	Paper	Code	Year
1	CMX (SegFormer-B4)	62.1	82.6	–	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers	huaaaliu/rgbx_semantic_segmentation	2022
2	CMX (SegFormer-B2)	61.2	82.3	–	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers	huaaaliu/rgbx_semantic_segmentation	2022
3	ShapeConv-101	60.6	82.7	70.0	ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation	hanchaoleng/shapeconv	2021
4	Linear Fusion (Segformer B2)	57.16	–	–	Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation	harshm121/m3l	2023
5	MMAF-Net-152	52.9	76.5	62.3	Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images		2019
6	Depth-aware CNN	39.5	65.4	55.5	Depth-aware CNN for RGB-D Segmentation	laughtervv/DepthAwareCNN · iriszero/DepthAwareCNNplus · aksh1501/DepthAware_CNN_edit · +1	2018
7	CMX (SegFormer-B4)	62.1	82.6	–	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers	huaaaliu/rgbx_semantic_segmentation	2022
8	CMX (SegFormer-B2)	61.2	82.3	–	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers	huaaaliu/rgbx_semantic_segmentation	2022
9	ShapeConv-101	60.6	82.7	70.0	ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation	hanchaoleng/shapeconv	2021
10	Linear Fusion (Segformer B2)	57.16	–	–	Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation	harshm121/m3l	2023
11	MMAF-Net-152	52.9	76.5	62.3	Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images		2019
12	Depth-aware CNN	39.5	65.4	55.5	Depth-aware CNN for RGB-D Segmentation	laughtervv/DepthAwareCNN · iriszero/DepthAwareCNNplus · aksh1501/DepthAware_CNN_edit · +1	2018