PSNR: 26.25SSIM: 0.926VMAF: 47.19
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: 26.68SSIM: 0.929VMAF: 51.21
Average PSNR: 48.23
PSNR: 25.89SSIM: 0.917VMAF: 36.46
PSNR: 27.28SSIM: 0.937VMAF: 57.39
PSNR: 27.14SSIM: 0.937VMAF: 56.45
SSIM: 0.753PSNR: 26.83TIoU: 0.684
PSNR: 26.99SSIM: 0.933VMAF: 51.96
PSNR: 26.12SSIM: 0.916VMAF: 56.86
PSNR: 27.29SSIM: 0.936VMAF: 56.69
PSNR: 27.23SSIM: 0.936VMAF: 57.14
PSNR: 26.97SSIM: 0.933VMAF: 55.45
SSIM: 0.591PSNR: 20.53TIoU: 0.539
PSNR: 27.42SSIM: 0.939VMAF: 57.91
PSNR: 30.96LPIPS: 0.349SSIM: 0.852
PSNR: 26.60SSIM: 0.933VMAF: 61.20
PSNR: 27.42SSIM: 0.939VMAF: 57.79
PSNR: 26.33SSIM: 0.929VMAF: 60.39
PSNR: 26.92SSIM: 0.932VMAF: 53.96
BSQ-rate over ERQA: 0.77BSQ-rate over Subjective Score: 0.196BSQ-rate over VMAF: 0.775BSQ-rate over PSNR: 0.675
SSIM: 0.671PSNR: 23.42TIoU: 0.539