search

raywzy / Bringing-Old-Films-Back-to-Life

Bringing Old Films Back to Life (CVPR 2022)
http://raywzy.com/Old_Film/
516 stars 51 forks source link

Hi, can you mention the probable date to release training code? #1

Open tawsinDOTuddin opened 2 years ago

AlexanderKozhevin commented 2 years ago

@tawsinDOTuddin do you need some help? I will be happy to prepare google colab

tawsinDOTuddin commented 2 years ago

I am working on old video restoration as my masters thesis. And so far I have been following deepremaster [1] which is the most relevant one for old video restoration. However, due to lackings of guided structural artifacts learning (using only L1 loss), it was giving me unstable learning like it was not paying attention to the artifacts. It is interesting to see how you implement the idea you guys have to improve structural learning and that is why I am curious about the code implementation and its release date. Thank you.

[1] Iizuka, S. and Simo-Serra, E., 2019. Deepremaster: temporal source-reference attention networks for comprehensive video enhancement. ACM Transactions on Graphics (TOG), 38(6), pp.1-13.

On Sat, 2 Apr 2022, 12:35 pm Alexander Kozhevin, @.***> wrote:

@tawsinDOTuddin https://github.com/tawsinDOTuddin do you need some help? I will be happy to prepare google colab

— Reply to this email directly, view it on GitHub https://github.com/raywzy/Bringing-Old-Films-Back-to-Life/issues/1#issuecomment-1086611421, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFP5ZZIN77PXTCNZACXGHFLVDAPHZANCNFSM5SKXZGAQ . You are receiving this because you were mentioned.Message ID: @.***>

martinva commented 2 years ago

I'm also very interested in your project. Would it be possible to access the code? I would be glad to collaborate training models if needed. Thanks.

YourSonnet18 commented 2 years ago

@raywzy My research subject is also old film restoration, so this work is a helpful reference for me. I'm also looking forward to the training code being released. In addition to the model architecture, there are some other details I want to figure out, for example, the temporal frame rendering process to create artificial data. Thank you!

AlexanderKozhevin commented 2 years ago

Is there any updates? Maybe I can help. I've temporary access to graphcore IPU.