notesum.ai

Published at December 10

EchoIR: Advancing Image Restoration with Echo Upsampling and Bi-Level Optimization

cs.CV

eess.IV

Released Date: December 10, 2024

Authors: Yuhan He¹, Yuchun He¹

Aff.: ¹University of Sydney

Arxiv: http://arxiv.org/pdf/2412.07225v1

Refer to caption

	Test100		Rain100H		Rain100L		Test2800		Test1200		Average
Methods	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$
DerainNet (Fu et al. 2017a)	22.77	0.810	14.92	0.592	27.03	0.884	24.31	0.861	23.38	0.835	22.48	0.796
SEMI (Wei et al. 2019)	22.35	0.788	16.56	0.486	25.03	0.842	24.43	0.782	26.05	0.822	22.88	0.744
PReNet (Ren et al. 2019)	24.81	0.851	26.77	0.858	32.44	0.950	31.75	0.916	31.36	0.911	29.42	0.897
MSPFN (Jiang et al. 2020)	27.50	0.876	28.66	0.860	32.40	0.933	32.82	0.930	32.39	0.916	30.75	0.903
MPRNet (Zamir et al. 2021)	30.27	0.897	30.41	0.890	36.40	0.965	33.64	0.938	32.91	0.916	32.73	0.921
MFDNet (Wang et al. 2023)	30.78	0.914	30.48	0.899	37.61	0.973	33.55	0.939	33.01	0.925	33.08	0.930
DGUNet (Mou, Wang, and Zhang 2022)	30.32	0.899	30.66	0.891	37.42	0.969	33.68	0.938	33.23	0.920	33.06	0.923
SPAIR (Purohit et al. 2021)	30.35	0.909	30.95	0.892	36.93	0.969	33.34	0.936	33.04	0.922	32.91	0.926
Restormer (Zamir et al. 2022)	31.63	0.923	31.14	0.907	37.46	0.972	33.98	0.942	33.11	0.926	33.46	0.934
Burstormer (Dudhane et al. 2023)	31.72	0.930	31.20	0.911	37.59	0.982	34.09	0.949	33.25	0.932	33.57	0.941
EchoIR (ours)	32.17	0.939	31.58	0.926	38.04	0.993	34.41	0.953	33.66	0.947	33.97	0.952