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

								Paper Title
ESRGAN	0.948	0.735	1.004	27.33	0	0.808	5.353	ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
BasicVSR	0.934	0.75	2.128	31.443	0.709	0.9	7.186	BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
TMNet	0.931	0.712	1.136	30.364	0.549	0.885	6	Temporal Modulation Network for Controllable Space-Time Video Super-Resolution
VRT	0.929	0.758	2.778	31.669	0.722	0.902	7.628	VRT: A Video Restoration Transformer
HCFlow	0.923	0.713	0.066	26.067	0	0.791	4.262	Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
DBVSR	0.921	0.737	0.241	31.071	0.629	0.894	6.947	Deep Blind Video Super-resolution
D3Dnet	0.915	0.674	0.041	29.703	0.549	0.876	5.066	Deformable 3D Convolution for Video Super-Resolution
RealSR	0.911	0.69	0.352	25.989	0	0.767	5.286	Real-World Super-Resolution via Kernel Estimation and Noise Injection
SOF-VSR-BI	0.904	0.66	0.571	29.381	0.557	0.872	4.805	Deep Video Super-Resolution using HR Optical Flow Estimation
LGFN	0.903	0.74	0.667	31.291	0.629	0.898	6.505	Local-Global Fusion Network for Video Super-Resolution
Real-ESRGAN	0.895	0.663	1.01	24.441	0	0.774	5.392	Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
SOF-VSR-BD	0.895	0.647	0.699	25.986	0.557	0.831	4.863	Deep Video Super-Resolution using HR Optical Flow Estimation
SwinIR	0.895	0.618	0.407	25.12	0	0.782	4.799	SwinIR: Image Restoration Using Swin Transformer
DynaVSR-R	0.884	0.709	0.177	28.377	0.557	0.865	6.136	DynaVSR: Dynamic Adaptive Blind Video Super-Resolution
COMISR	0.879	0.654	1.613	26.708	0.619	0.84	5.637	COMISR: Compression-Informed Video Super-Resolution
SRMD	0.877	0.594	5.882	27.672	0	0.834	3.468	Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
Real-ESRnet	0.871	0.598	1.019	27.195	0	0.824	3.697	Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
DUF-28L	0.87	0.645	0.418	25.852	0.549	0.83	5.324	Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation
DUF-16L	0.868	0.641	0.605	24.606	0.549	0.828	5.124	Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation
waifu2x-cunet	0.861	0.6	1.282	27.716	0	0.838	3.308	-

0 of 32 row(s) selected.

Command Palette

Video Super Resolution On Msu Vsr Benchmark

評価指標

評価結果