Comments (5)
Hi there,
That's about right, the only thing is that for display-referred the factor is 1000 (corresponding to 1000 nits) and not 1024. For scene referred it's the original image maximum.
Also, in the paper it's stated that "The scaling is done to match the 0.1 and 99.9 percentiles of the predictions with the corresponding percentiles of the HDR test images". This is done to better avoid outliers (in all model predictions and in the original HDR images).
This means that, e.g. for display referred, instead of matching 0 - >0 and 1 - > 1000 you match perc(prediction, 0.1) -> 1 and perc(prediction, 99.9) -> 999.
For scene-referred you use the original image percentiles instead of 1 and 999.
This matching is simple linear interpolation.
Hope this helps.
Best,
Demetris
from hdr-expandnet.
So, for display referred
low, high = np.percentile(x, (0.1, 99.9)) // x could be in range of 0-1 or 0-n
y=np.interp(x, [low, high], [1, 999]).astype(np.float32)
for scene-referred
low, high = np.percentile(x, (0.1, 99.9)) // x could be in range of 0-1 or 0-n
gt_low, gt_high = np.percentile(gt, (0.1, 99.9))
y=np.interp(x, [low, high], [gt_low, gt_high]).astype(np.float32)
Do these code look good to you?
from hdr-expandnet.
from hdr-expandnet.
Got it! Thank you for helping me out!
from hdr-expandnet.
No worries, glad to help!
from hdr-expandnet.
Related Issues (20)
- Image range processing in the experiment stage HOT 1
- Where can I get the dataset? HOT 1
- Inquiry about Dataset HOT 3
- Question about video dataset HOT 1
- About the performance of the model in training HOT 6
- durand tmo is not avalable HOT 3
- Training, iterations and pictureamount HOT 7
- Which version of PyTorch do you use in this project? HOT 1
- about train data formats HOT 1
- about hdr image save HOT 3
- results in shadows HOT 21
- Not working at all HOT 8
- why it is not giving a hdr output? HOT 13
- Any updates on Training Source? HOT 4
- First line almost black HOT 1
- How to get the in-house HDR image? HOT 1
- Can expanded output be in .exr format instead of .hdr format? or need more details on .hdr HOT 2
- iterating over png/jpg dataset from a folder HOT 4
- The domain of pre-train model HOT 3
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 hdr-expandnet.