Table 2.

Quantitative comparison (average PSNR) with different color image denoising methods on a benchmark dataset.

Method	CBSD68 (Martin et al., 2001)			Kodak24 (Franzen, 1999)			McMaster (Zhang et al., 2011)			Urban100 (Huang et al., 2015)
	σ = 15	σ = 25	σ = 50	σ = 15	σ = 25	σ = 50	σ = 15	σ = 25	σ = 50	σ = 15	σ = 25	σ = 50
FFDNet	33.87	31.21	27.96	34.63	32.13	28.98	34.66	32.35	29.18	33.87	31.21	27.96
DnCNN	33.90	31.24	27.95	34.60	32.16	29.05	33.45	31.52	28.62	33.90	31.24	27.95
DSNet	33.91	31.28	28.05	34.63	32.16	29.05	34.67	32.40	29.28	33.91	31.28	28.05
RPCNN	-	31.28	28.05	34.63	32.13	28.98	34.66	32.35	29.18	-	31.28	28.05
BRDNet	34.10	31.43	28.16	34.88	32.41	29.22	35.08	32.75	29.52	34.10	31.43	28.16
TORNet (Ours)	34.29	31.60	28.42	35.16	32.6/5	29.58	35.39	33.03	29.98	34.93	32.25	28.80

Bold values indicate the best performance for each column.