Video Super Resolution On Msu Super 1

评估指标

BSQ-rate over ERQA

BSQ-rate over LPIPS

BSQ-rate over MS-SSIM

BSQ-rate over PSNR

BSQ-rate over VMAF

评测结果

各个模型在此基准测试上的表现结果

						Paper Title	Repository
bicubic + uavs3e	21.965	18.057	5.068	7.372	7.026	-	-
RealSR + vvenc	21.965	18.344	11.643	15.144	10.67	Real-World Super-Resolution via Kernel Estimation and Noise Injection	-
bicubic + aomenc	21.965	17.458	2.888	8.395	6.797	-	-
bicubic + vvenc	21.965	16.894	5.735	12.787	8.635	-	-
TMNet + aomenc	21.798	6.276	10.322	15.144	4.667	Temporal Modulation Network for Controllable Space-Time Video Super-Resolution
TMNet + vvenc	21.303	13.988	1.813	9.43	1.795	Temporal Modulation Network for Controllable Space-Time Video Super-Resolution
RSDN + aomenc	20.617	14.574	11.643	15.144	10.67	Video Super-Resolution with Recurrent Structure-Detail Network
SOF-VSR-BI + vvenc	18.844	11.273	4.882	9.245	4.527	Deep Video Super-Resolution using HR Optical Flow Estimation
SOF-VSR-BI + x265	18.545	11.236	4.558	9.07	3.565	Deep Video Super-Resolution using HR Optical Flow Estimation
LGFN + vvenc	18.342	11.759	0.889	5.768	1.626	Local-Global Fusion Network for Video Super-Resolution	-
VRT + vvenc	18.333	11.496	0.836	5.777	0.652	VRT: A Video Restoration Transformer
BasicVSR + vvenc	18.333	11.561	0.919	5.781	0.676	BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
RSDN + uavs3e	18.327	13.844	11.643	15.144	9.796	Video Super-Resolution with Recurrent Structure-Detail Network
RBPN + vvenc	18.314	11.777	0.884	5.783	0.689	Recurrent Back-Projection Network for Video Super-Resolution
EGVSR + aomenc	16.733	5.67	11.643	15.144	10.67	Real-Time Super-Resolution System of 4K-Video Based on Deep Learning
bicubic + x265	16.014	15.363	4.563	6.473	6.469	-	-
DBVSR + vvenc	15.988	11.435	0.898	5.765	0.698	Deep Blind Video Super-resolution
SOF-VSR-BD + vvenc	15.958	13.494	2.112	8.027	6.41	Deep Video Super-Resolution using HR Optical Flow Estimation
SOF-VSR-BD + aomenc	15.11	4.034	7.546	13.076	7.464	Deep Video Super-Resolution using HR Optical Flow Estimation
RSDN + vvenc	14.95	4.866	9.138	14.061	10.145	Video Super-Resolution with Recurrent Structure-Detail Network

0 of 85 row(s) selected.