Video Super Resolution On Msu Vsr Benchmark

評価指標

1 - LPIPS

ERQAv1.0

FPS

PSNR

QRCRv1.0

SSIM

Subjective score

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

比較表

モデル名	1 - LPIPS	ERQAv1.0	FPS	PSNR	QRCRv1.0	SSIM	Subjective score
video-super-resolution-with-recurrent	0.819	0.667	1.961	25.321	0.619	0.826	5.566
revisiting-temporal-modeling-for-video-super	0.856	0.617	2.74	23.786	0.549	0.789	5.02
real-esrgan-training-real-world-blind-super	0.871	0.598	1.019	27.195	0	0.824	3.697
hierarchical-conditional-flow-a-unified	0.923	0.713	0.066	26.067	0	0.791	4.262
vrt-a-video-restoration-transformer	0.929	0.758	2.778	31.669	0.722	0.902	7.628
real-esrgan-training-real-world-blind-super	0.895	0.663	1.01	24.441	0	0.774	5.392
local-global-fusion-network-for-video-super	0.903	0.74	0.667	31.291	0.629	0.898	6.505
comisr-compression-informed-video-super	0.879	0.654	1.613	26.708	0.619	0.84	5.637
real-world-super-resolution-via-kernel	0.911	0.69	0.352	25.989	0	0.767	5.286
モデル 10	0.861	0.6	1.282	27.716	0	0.838	3.308
モデル 11	0.856	0.57	3.125	27.176	0	0.819	2.739
tdan-temporally-deformable-alignment-network	0.721	0.706	0.493	30.244	0.609	0.883	5.454
blind-face-restoration-via-deep-multi-scale	0.623	0.339	0.909	24.832	0	0.759	0.277
temporal-modulation-network-for-controllable	0.931	0.712	1.136	30.364	0.549	0.885	6
deep-video-super-resolution-network-using	0.87	0.645	0.418	25.852	0.549	0.83	5.324
deep-video-super-resolution-using-hr-optical	0.904	0.66	0.571	29.381	0.557	0.872	4.805
learning-a-single-convolutional-super	0.877	0.594	5.882	27.672	0	0.834	3.468
iseebetter-spatio-temporal-video-super	0.741	0.748	0.045	31.104	0.629	0.896	6.809
recurrent-back-projection-network-for-video	0.74	0.746	0.043	31.407	0.629	0.899	7.068
esrgan-enhanced-super-resolution-generative	0.948	0.735	1.004	27.33	0	0.808	5.353
deformable-3d-convolution-for-video-super	0.915	0.674	0.041	29.703	0.549	0.876	5.066
dynavsr-dynamic-adaptive-blind-video-super	0.884	0.709	0.177	28.377	0.557	0.865	6.136
basicvsr-the-search-for-essential-components	0.934	0.75	2.128	31.443	0.709	0.9	7.186
deep-video-super-resolution-using-hr-optical	0.895	0.647	0.699	25.986	0.557	0.831	4.863
revisiting-temporal-modeling-for-video-super	0.842	0.627	2.567	24.252	0.557	0.79	5.35
real-time-single-image-and-video-super	0.765	0.521	3.333	26.714	0	0.811	2.099
towards-real-world-blind-face-restoration	0.793	0.538	1.562	24.195	0	0.745	2.686
deep-blind-video-super-resolution	0.921	0.737	0.241	31.071	0.629	0.894	6.947
deep-video-super-resolution-network-using	0.868	0.641	0.605	24.606	0.549	0.828	5.124
dynavsr-dynamic-adaptive-blind-video-super	0.859	0.643	0.15	29.011	0.549	0.864	4.359
swinir-image-restoration-using-swin	0.895	0.618	0.407	25.12	0	0.782	4.799
video-super-resolution-with-temporal-group-1	0.859	0.669	0.706	25.786	0.549	0.831	5.529