Comments (2)
Hi JUGGHM,
Thank you for your question.
In this case, the normalized convolution formulation will become more nasty and I will include matrix inversion for each pixel in the image.
If you look at equation 3 in the paper, you can see that if you have more than 1 basis, you will add this in the columns of matrix B. Then you will need to estimate the coordinates r for each pixel in the image with respect to this basis.
I hope this answers your qeustion.
from nconv.
Thanks for your sincere answer! I have found a easy way to understand: write down the expressions for conv (on 1d), than normalized conv, and than normalized conv with confidence. Finally I find that B=1 basis vector is actually enough for general convolution operations, and that we don't need two or more basis vectors in B.
Hi JUGGHM,
Thank you for your question.
In this case, the normalized convolution formulation will become more nasty and I will include matrix inversion for each pixel in the image.
If you look at equation 3 in the paper, you can see that if you have more than 1 basis, you will add this in the columns of matrix B. Then you will need to estimate the coordinates r for each pixel in the image with respect to this basis.
I hope this answers your qeustion.
from nconv.
Related Issues (11)
- Trained weights HOT 1
- Confidence map HOT 1
- About NYU pretrained weight HOT 3
- evaluate function HOT 2
- about pos_fn HOT 2
- about cached memory when running the code
- ValueError: num_samples should be a positive integeral value, but got num_samples=0 HOT 2
- Which dataset used for training HOT 2
- How to produce the pretrained model for unguided network HOT 2
- Bug when try LiDAR only HOT 2
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 nconv.