Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Spectral Reconstruction On Arad 1K

Metrics

MRAE

PSNR

RMSE

Results

Performance results of various models on this benchmark

Model Name	MRAE	PSNR	RMSE	Paper Title	Repository
HDNet	0.2048	32.13	0.0317	HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
MST++	0.1645	34.32	0.0248	MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction
HRNet	0.3476	26.89	0.0550	Hierarchical Regression Network for Spectral Reconstruction from RGB Images
MST-L	0.1772	33.90	0.0256	Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
EDSR	0.3277	28.29	0.0437	Enhanced Deep Residual Networks for Single Image Super-Resolution
Restormer	0.1833	33.40	0.0274	Restormer: Efficient Transformer for High-Resolution Image Restoration
AWAN	0.2500	31.22	0.0367	Adaptive Weighted Guided Image Filtering for Depth Enhancement in Shape-From-Focus	-
MIRNet	0.1890	33.29	0.0274	Learning Enriched Features for Real Image Restoration and Enhancement
HSCNN+	0.3814	26.36	0.0588	HSCNN: A Hybrid-Siamese Convolutional Neural Network for Extremely Imbalanced Multi-label Text Classification	-
MPRNet	0.1817	33.50	0.0270	Multi-Stage Progressive Image Restoration
HINet	0.2032	32.51	0.0303	HINet: Half Instance Normalization Network for Image Restoration

0 of 11 row(s) selected.