Comments (5)
Hi Collin, It sounds like you may want a white balancing algorithm. We are actually playing around with re-purposing our algorithm for white balancing, but don't have anything mature on it yet. Thanks for your interest!
Richard
from colorization.
Thanks! Yes, that is close, but consistency is the key and AWB's tend to vary depending on the illuminate pixel samples... making it very picture-dependent... meaning the AWB( P ) != AWB( P` ). What fascinated me about your system is it could have the effect I need without balancing at all, or perhaps only balancing a grayscale variant of the picture.
If you do wind up implementing this, or even want someone to assist in testing, I would be interested. Do you have a prefered notification method for updating on progress of such things?
from colorization.
Hi, you can check my webpage or my group members webpages (find them on here: https://people.eecs.berkeley.edu/~efros/) for our most recent work!
from colorization.
Did you ever do anything with white balancing?
from colorization.
We didn't end up pursuing that. We may get back to it at some point. Thanks!
from colorization.
Related Issues (20)
- How to realize image segmentation?
- Images classifier
- CoreML version
- requirements.txt HOT 1
- does not work HOT 1
- ncnn colorization-siggraph17
- "colorization_release_v2.caffemodel" file not available anymore
- the response is 403 HOT 3
- import caffe HOT 1
- Pretrained weights are inaccessible HOT 5
- C ++ interface for colorization.
- what is the image augmentation strategy while training on current demo release? HOT 2
- PyTorch Example
- get colored images from my pretrained caffemodel HOT 13
- How to find the 313 bins HOT 1
- Resume Training
- annealed mean implementation
- Model architecture does not have H*W*Q size tensors for (a,b) probability HOT 1
- Need help not sure whats the issue is
- colorization is not working properly, output is not good
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 colorization.