Comments (1)
Hi @yx-chan131,
Since we are using U-Net for estimating shadow mattes, the size of the input images has to be multipliers of 256. You can just use the input of size 256x256 to produce the shadow parameters. And then use the input of size 768*768 to produce a high-res matte layer. You then resize the matte layer to the original size of the input and use them to generate the shadow-free image at its original size.
Please let me know how it goes, I am happy to assist you further if necessary :)
from sid.
Related Issues (20)
- Questions about evaluation HOT 9
- I-Net HOT 1
- ISTD+ dataset HOT 2
- Internal work array size computation failed: -5 HOT 1
- Could you provide the mask utilized for testing in TPAMI2020 work? HOT 2
- about infer, is this method need a shadow mask first???
- evaluation problem HOT 1
- mask of ISTD_crf
- Results of SP+M+I-Net~(TPAMI) on the SBU-TimeLapse dataset.
- Thanks for your contribution,and I want to ask where is the models.cycle_gan_model?
- Questions about shadow parameters predictions HOT 1
- Where is the dataset of relit images? They don't seem to be in ISTD HOT 2
- Question about the augmented ISTD dataset HOT 1
- How to train this model on customer dataset HOT 2
- When will you have the code for paper "From Shadow Segmentation to Shadow Removal" open to public?
- How to obtain input['penumbra']? HOT 1
- no link to the adjusted ISTD dataset? HOT 2
- CUDA version
- How to use DataSet?
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 sid.