SOTA Parallel Imaging Reconstruction on knee dataset CORPD-weighted in-distribution (test) and PapersWithCode

37.05PSNR

fully-learned filters and time conditioning (FLF+TC)

Updated 22d ago

Evaluation Results

Method
fully-learned filters and time conditioning (FLF+TC) 2026.05	37.05	92	0.24
end-to-end variational network (VN) 2026.05	36.92	92	0.24
fully-learned filters (FLF) 2026.05	36.68	91	0.26
Shearlet (SH) 2026.05	36.19	91	0.29
fully-learned filters and time conditioning (FLF+TC) 2026.05	35.84	89	0.32
fully-learned filters (FLF) 2026.05	35.75	89	0.32
Shearlet (SH) 2026.05	35.6	89	0.33
fully-learned filters and time conditioning (FLF+TC) 2026.05	35.5	89	0.36
fully-learned filters (FLF) 2026.05	35.39	89	0.36
fully-learned filters and time conditioning (FLF+TC) 2026.05	35.32	89	0.36
fully-learned filters (FLF) 2026.05	35.29	89	0.36
fully-learned filters and time conditioning (FLF+TC) 2026.05	35.1	87	0.38
fully-learned filters (FLF) 2026.05	34.94	87	0.38
Shearlet (SH) 2026.05	34.64	88	0.41
Shearlet (SH) 2026.05	34.54	87	0.42
Deep-JSense (DJS) 2026.05	34.45	90	0.46
total variation (TV) 2026.05	34.35	86	0.44
Shearlet (SH) 2026.05	34.3	88	0.44
Deep-JSense (DJS) 2026.05	33.84	90	0.53
total variation (TV) 2026.05	33.65	84	0.51
total variation (TV) 2026.05	33.24	82	0.56
Deep-JSense (DJS) 2026.05	33.2	90	1.85
total variation (TV) 2026.05	33	83	0.59
Deep-JSense (DJS) 2026.05	32.79	86	0.71
end-to-end variational network (VN) 2026.05	32.16	89	0.69
Zero filled (ZF) 2026.05	32.15	84	0.78
total variation (TV) 2026.05	31.86	82	0.81
Zero filled (ZF) 2026.05	31.13	81	0.97
Zero filled (ZF) 2026.05	28.76	75	1.67
Zero filled (ZF) 2026.05	27.19	74	2.37
Deep-JSense (DJS) 2026.05	25.44	80	6.63
end-to-end variational network (VN) 2026.05	24.72	67	3.29
Zero filled (ZF) 2026.05	24.14	69	4.96
end-to-end variational network (VN) 2026.05	23.53	73	4.33
end-to-end variational network (VN) 2026.05	20.56	69	6.55