notesum.ai

Published at November 10

Local Implicit Wavelet Transformer for Arbitrary-Scale Super-Resolution

cs.CV

cs.AI

Released Date: November 10, 2024

Authors: Minghong Duan¹, Linhao Qu¹, Shaolei Liu¹, Manning Wang¹

Aff.: ¹Digital Medical Research Center, Fudan University, Shanghai, China

Arxiv: http://arxiv.org/abs/2411.06442v1

Backbone	Methods	$\times 2$	$\times 3$	$\times 4$	$\times 6$	$\times 12$	$\times 18$	$\times 24$	$\times 30$
-	Bicubic	31.01	28.22	26.66	24.82	22.27	21	20.19	19.59
	EDSR-baseline [Lim et al.(2017)Lim, Son, Kim, Nah, and Mu Lee]	34.55	30.9	28.94	-	-	-	-	-
	EDSR-Meta-SR [Hu et al.(2019)Hu, Mu, Zhang, Wang, Tan, and Sun]	34.64	30.93	28.92	26.61	23.55	22.03	21.06	20.37
	EDSR-LIIF [Chen et al.(2021b)Chen, Liu, and Wang]	34.67	30.96	29.00	26.75	23.71	22.17	21.18	20.48
	EDSR-UltraSR [Xu et al.(2021)Xu, Wang, and Shi]	34.69	31.02	29.05	26.81	23.75	22.21	21.21	20.51
	EDSR-IPE [Liu et al.(2021)Liu, Guo, and Zhang]	34.72	31.01	29.04	26.79	23.75	22.21	21.22	20.51
	EDSR-LTE [Lee and Jin(2022)]	34.72	31.02	29.04	26.81	23.78	22.23	21.24	20.53
EDSR [Lim et al.(2017)Lim, Son, Kim, Nah, and Mu Lee]	EDSR-LIWT(ours)	34.79	31.12	29.15	26.91	23.86	22.31	21.30	20.60
	RDN-baseline [Zhang et al.(2018b)Zhang, Tian, Kong, Zhong, and Fu]	34.94	31.22	29.19	-	-	-	-	-
	RDN-Meta-SR [Hu et al.(2019)Hu, Mu, Zhang, Wang, Tan, and Sun]	35.00	31.27	29.25	26.88	23.73	22.18	21.17	20.47
	RDN-LIIF [Chen et al.(2021b)Chen, Liu, and Wang]	34.99	31.26	29.27	26.99	23.89	22.34	21.31	20.59
	RDN-UltraSR [Xu et al.(2021)Xu, Wang, and Shi]	35.00	31.30	29.32	27.03	23.73	22.36	21.33	20.61
	RDN-IPE [Liu et al.(2021)Liu, Guo, and Zhang]	35.04	31.32	29.32	27.04	23.93	22.38	21.34	20.63
	RDN-LTE [Lee and Jin(2022)]	35.04	31.32	29.33	27.04	23.95	22.40	21.36	20.64
RDN [Zhang et al.(2018b)Zhang, Tian, Kong, Zhong, and Fu]	RDN-LIWT(ours)	35.07	31.36	29.39	27.11	24.03	22.47	21.43	20.70
	SwinIR-baseline [Liang et al.(2021)Liang, Cao, Sun, Zhang, Van Gool, and Timofte]	34.94	31.22	29.19	-	-	-	-	-
	SwinIR-Meta-SR [Hu et al.(2019)Hu, Mu, Zhang, Wang, Tan, and Sun]	35.15	31.40	29.33	26.94	23.80	22.26	21.26	20.54
	SwinIR-LIIF [Chen et al.(2021b)Chen, Liu, and Wang]	35.17	31.46	29.46	27.15	24.02	22.43	21.40	20.67
	SwinIR-LTE [Lee and Jin(2022)]	35.24	31.50	29.51	27.20	24.09	22.50	21.47	20.73
SwinIR [Liang et al.(2021)Liang, Cao, Sun, Zhang, Van Gool, and Timofte]	SwinIR-LIWT(ours)	35.25	31.53	29.55	27.25	24.15	22.56	21.52	20.77