notesum.ai

Published at December 9

U-Know-DiffPAN: An Uncertainty-aware Knowledge Distillation Diffusion Framework with Details Enhancement for PAN-Sharpening

cs.CV

eess.IV

Released Date: December 9, 2024

Authors: Sungpyo Kim¹, Jeonghyeok Do¹, Jaehyup Lee², Munchurl Kim¹

Aff.: ¹KAIST; ²KNU

Arxiv: http://arxiv.org/pdf/2412.06243v1

[Uncaptioned image]

GF2 Dataset							Reduced-Resolution					Full-Resolution
Types	Methods	Publications	PSNR $\uparrow$	SSIM $\uparrow$	SAM $\downarrow$	ERGAS $\downarrow$	SCC $\uparrow$	Q4 $\uparrow$	$D_{\lambda}\downarrow$	$D_{s}\downarrow$	HQNR $\uparrow$
Non-DMs	PanNet [61]	ICCV 2017	39.197	0.959	1.050	1.038	0.975	0.963	0.020	0.052	0.929
	MSDCNN [64]	JSTARS 2018	40.730	0.971	0.946	0.862	0.983	0.972	0.026	0.079	0.898
	FusionNet [56]	ICCV 2021	39.866	0.966	0.971	0.960	0.980	0.967	0.034	0.105	0.865
	LAGConv [26]	AAAI 2022	41.147	0.974	0.886	0.816	0.985	0.974	0.030	0.078	0.895
	S2DBPN [68]	TGRS 2023	42.686	0.980	0.772	0.686	0.990	0.981	0.020	0.046	0.935
	DCPNet [72]	TGRS 2024	42.312	0.979	0.806	0.724	0.988	0.980	0.024	0.024	0.953
	CANConv [15]	CVPR 2024	43.166	0.982	0.722	0.653	0.991	0.983	0.019	0.063	0.919
Diffusion Models	PanDiff [33]	TGRS 2023	42.827	0.980	0.767	0.674	0.990	0.981	0.020	0.045	0.936
	TMDiff [59]	TGRS 2024	41.896	0.977	0.764	0.754	0.988	0.979	0.029	0.030	0.942
	FSA-S	Ours	44.585	0.986	0.624	0.548	0.993	0.987	0.018	0.037	0.944
	FSA-T	Ours	44.757	0.988	0.603	0.537	0.994	0.988	0.017	0.029	0.953