search

ryanxingql / stdf-pytorch

Implementation of "Spatio-Temporal Deformable Convolution for Compressed Video Quality Enhancement" (AAAI'20).
https://www.aiide.org/ojs/index.php/AAAI/article/view/6697
Apache License 2.0
155 stars 20 forks source link

How to visualize the offsets in each frame as Fig 3 in the paper? #2

Closed zzwei1 closed 3 years ago

zzwei1 commented 3 years ago

Nice work! I wonna know how to visualize the offsets in each frame as Fig 3 in the paper, is there some guidiance? image

ryanxingql commented 3 years ago

Hi!

Unfortunately, I am not the author of this work. I just implement it by my own. For accurate details, you can email the author Jianing Deng. He is really a nice guy hhh.

In my opinon, the offset is explicitly learned in our network: https://github.com/RyanXingQL/STDF-PyTorch/blob/9acce89fe2adfbfd6a1783c2d9f48c30dc4988bb/net_stdf.py#L99 So you can simply visualize the learned feature map here.

zzwei1 commented 3 years ago

Hi!

Unfortunately, I am not the author of this work. I just implement it by my own. For accurate details, you can email the author Jianing Deng. He is really a nice guy hhh.

In my opinon, the offset is explicitly learned in our network: https://github.com/RyanXingQL/STDF-PyTorch/blob/9acce89fe2adfbfd6a1783c2d9f48c30dc4988bb/net_stdf.py#L99

So you can simply visualize the learned feature map here.

Thanks for your guidiance! I 'll try it!