Comments (5)
AlexanderKozhevin
commented on June 26, 2024
3
@tawsinDOTuddin do you need some help?
I will be happy to prepare google colab
from bringing-old-films-back-to-life.
tawsinDOTuddin
commented on June 26, 2024
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
<#1 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AFP5ZZIN77PXTCNZACXGHFLVDAPHZANCNFSM5SKXZGAQ>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
from bringing-old-films-back-to-life.
martinva
commented on June 26, 2024
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.
from bringing-old-films-back-to-life.
YourSonnet18
commented on June 26, 2024
@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!
from bringing-old-films-back-to-life.
AlexanderKozhevin
commented on June 26, 2024
Is there any updates?
Maybe I can help.
I've temporary access to graphcore IPU.
from bringing-old-films-back-to-life.
Related Issues (20)
- How to train the model for colorization task? HOT 2
- Tutorial please
- Can this run on non-nvidia cards? HOT 2
- Test error HOT 3
- How to get the same output size as the input image? HOT 1
- Any train or test code for the colorization task? HOT 4
- Scratches are not removed after processing HOT 1
- Preserve colors in color video sources HOT 7
- Can I continue training when the training progress is terminated？
- How to generate paired data via the Video Degradation Model?
- Colab notebook HOT 1
- How to get the colorized version after obtaining the restored black-and-white one? HOT 3
- Optical Flow works bad in occlusion case
- Is there anywhere to get Test, validation set for dataset?
- An test error in project HOT 1
- non-empty 3D or 4D input tensor expected but got ndim: 4
- Explaning the commandline
- How should the validation set be obtained, the same as the training set?
- How to output only converted video?
- need colorization
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from bringing-old-films-back-to-life.