PSNR: 28.04SSIM: 0.8570
Papers with Code · CC BY-SA 4.0
Video Super-Resolution
Video Super-Resolution is a computer vision task that aims to increase the resolution of a video sequence, typically from lower to higher resolutions. The goal is to generate high-resolution video frames from low-resolution input, improving the overall quality of the video.
<span style="color:grey; opacity: 0.6">( Image credit: Detail-revealing Deep Video Super-Resolution )</span>
논문
PSNR: 27.17SSIM: 0.8205
PSNR: 27.69SSIM: 0.8488
PSNR: 29.42SSIM: 0.8795
PSNR: 39.93
PSNR: 29.04SSIM: 0.8753
Subjective score: 6.947ERQAv1.0: 0.737QRCRv1.0: 0.629SSIM: 0.894
PSNR: 27.38SSIM: 0.8329
Subjective score: 6.136ERQAv1.0: 0.709QRCRv1.0: 0.557SSIM: 0.865
PSNR: 27.85SSIM: 0.8503
PSNR: 27.48SSIM: 0.8388
PSNR: 26.69SSIM: 0.8103
SSIM: 0.504PSNR: 18.84TIoU: 0.598
Subjective score: 6.809ERQAv1.0: 0.748QRCRv1.0: 0.629SSIM: 0.896
PSNR: 28.7SSIM: 0.869
PSNR: 28.40SSIM: 0.8643
Subjective score: 6.505ERQAv1.0: 0.74QRCRv1.0: 0.629SSIM: 0.898
PSNR: 28.41SSIM: 0.8724
PSNR: 27.16SSIM: 0.8355
PSNR: 29.54SSIM: 0.8810
SSIM: 0.651PSNR: 23.13TIoU: 0.598
Subjective score: 6ERQAv1.0: 0.712QRCRv1.0: 0.549SSIM: 0.885
PSNR: 25.85SSIM: 0.7659
PSNR: 27.92SSIM: 0.8505
PSNR: 27.63SSIM: 0.8423