Comments (2)
Hi,
Basically, this function takes the latent code z as input and returns the output shape represented as a grid. The grid size is self.cell_grid_size*self.frame_grid_size (256 by default). You can find these parameters in the code:
self.cell_grid_size = 4
self.frame_grid_size = 64
For faster inference, the function will first compute a coarse shape on a coarse grid, whose size is defined by self.frame_grid_size. This part is commented by #get frame grid values
.
Then, for each voxel in the coarse grid, if it is adjacent to the shape boundary (the voxel is 0 but a neighbor voxel is 1, or the voxel is 1 but a neighbor voxel is 0), it will be recorded in a queue. The queue will only contain coarse voxels close to the shape boundary. This part is commented by #get queue and fill up ones
.
Then, we get the fine grid by only computing the voxels close to the shape boundary. The size of the fine grid is self.cell_grid_size*self.frame_grid_size, therefore each coarse voxel in the queue will be split into a grid of fine voxels, with grid size = self.cell_grid_size. Then the implicit field values of those fine voxels will be computed. This part is commented by #run queue
. Note that during this process, new coarse voxels will be put into the queue if they are identified as "adjacent to the shape boundary".
After that, the fine voxel grid is returned. Hope this explanation helps.
Best,
Zhiqin
from im-net-pytorch.
Thank you so much for your helpfulness and such a quick reply.
I will try my best to understand.
You are the best person in the world!
from im-net-pytorch.
Related Issues (20)
- Code for latent GAN HOT 1
- Reproducing for Point Cloud to Mesh Reconstruction HOT 2
- inconsistency with AE training config and data HOT 2
- Visualizing voxel grid HOT 2
- Question on data preprocessing step HOT 4
- Issues with reconstruction / Discrepancy in metric (CD) HOT 1
- Question on Inference HOT 3
- A concern about the loss function. HOT 6
- training loss keeps increasing for SVR task HOT 2
- About test HOT 8
- About testing HOT 9
- About the original voxel models from HSP HOT 2
- the training code of training font HOT 1
- Training with the ready-to-use data HOT 2
- Have you released the interpolation of 2D Letters? HOT 2
- Train imnet using other data HOT 8
- The issue of infinite loop here HOT 2
- IM-GAN for pytorch version HOT 1
- About the data preprocess HOT 1
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 im-net-pytorch.