A Network with Composite Loss and Parameter-free Chunking Fusion Block for Super-Resolution MR Image

Table 5

Comparative experimental results of the introduced loss function.

	L1 loss	L2 loss	Composite loss	PSNR	SSIM	RMSE
Ours	✓	—	—	33.89	0.9763	0.0214
Ours	—	✓	—	33.96	0.9772	0.0213
Ours	—	—	✓	34.52	0.9790	0.0200

Bold values highlight the optimal results.