search

yzxing87 / pytorch-deep-video-prior

[NeurIPS 2020] Blind Video Temporal Consistency via Deep Video Prior
118 stars 22 forks source link

Reproducing Evaluation Results #1

Closed greeneggsandyaml closed 3 years ago

greeneggsandyaml commented 3 years ago

Hello authors, thank you for your great work!

I am writing a blog post about your work and I was interested in reproducing the results completely (on DAVIS/the Bonneel dataset). Would it be possible for you to provide evaluation code or instructions as to evaluating E_warp and F_data for your method on these datasets?

All the best,

yzxing87 commented 3 years ago

Hi, thanks for your interest!

To evaluate E_warp, you need to install PWC-Net to calculate optical flow. Please follow the instruction here. F_data is actually measured by PSNR, which is easy to implement. 

def compute_psnr(img1, img2):
    mse = np.mean( (img1 - img2) ** 2 )
    if mse == 0:
        return 100
    PIXEL_MAX = 1.
    return 20 * math.log10(PIXEL_MAX / math.sqrt(mse))

We are preparing all our results and will make them public online for evaluation and further comparisons.

greeneggsandyaml commented 3 years ago

Hi, thank you for your response! I really appreciate it. I will work to reproduce the results and keep you updated. When I finish reproducing, I will close this issue :)