Comments (8)
@tangjilin see data_generation folder
from pixel2mesh.
@nywang16 Thanks very much!
from pixel2mesh.
Hi, @nywang16 After checking the https://github.com/nywang16/Pixel2Mesh/blob/master/GenerateData/4_make_auxiliary_dat_file.ipynb. I have the following confusions about the data generation part.
About the original data from shapenetcore.v1, are they all resized to be put in a unit cube, which are of size (-0.5,0.5)^3? And why would you choose ellipsoid with a size of (0.2,0.2,0.4) radius?
And you use your rendering_metacamera.txt annotations to transform 3d object to camera coordinates?
from pixel2mesh.
Hi @KnightOfTheMoonlight , our method is not sensitive to initial shape, you can also use sphere. The reason for using the ellipsoid as the initial may be that the average shape of the object is closer to the ellipsoid.
from pixel2mesh.
It is kind of sensitive though right? You want the initial mesh's vertices to project "nicely" over the input image so that the sampled image features which are placed on those vertices properly capture the information in the image. If the range of vertices when projected into images space is too small in either direction information about the object will be lost, and similarly if the range is too large. I would think any shape with uniformly distributed vertices in the range of (-0.5,0.5)^3 would be fine.
from pixel2mesh.
Hi, @EdwardSmith1884 . I don't think the initial shape is very sensitive. According to the performance of graph convolution during training, no matter what the initial shape is, it seems that graph convolution tends to learn the shape completely from scratch. The shape of the three-dimensional mesh output by the first few epochs and initial mesh are basically irrelevant, but is mainly affected by topology.
At the same time, I also agree that what you said may be a more natural approach to uniform sampling in three dimensions.
Specifically, our experiments in the ECCV supp are as follows.
from pixel2mesh.
I think these all do well because they basically have uniformly distributed vertices in the range of (-0.5,0.5)^3 . I would think if the ellipsoid was very thin in one dimension, or the sphere was 1/10 the scale it would do worse. I guess I mean shape doesn't really matter but scale does, at least I observed worse much worse accuracy when I didn't scale the initial mesh properly.
from pixel2mesh.
Hi,
Do you know how to download the dataset and unzip it from the link below?
https://drive.google.com/open?id=131dH36qXCabym1JjSmEpSQZg4dmZVQid
from pixel2mesh.
Related Issues (20)
- Train on dataset of images
- How do you train this on a own dataset of 3d models? HOT 3
- tensorflow.python.framework.errors_impl.InvalidArgumentError
- How to create our own datasets? HOT 1
- The passed save_path is not a valid checkpoint: Data/checkpoint/gcc.ckpt
- Question about GenerateData HOT 1
- Is 4_make_auxiliary_dat_file.ipynb supposed to generate the same formatted dat files as the ones in the gdrive of shapenet? HOT 2
- One problem about some trick things
- Pixel2Mesh commercial use inquiry
- How does converting the .xyz file to a .dat file work ? HOT 5
- How to get texture?
- No module named 'layers' HOT 2
- Is the support constant in all shapes(airplane, car, ellipsoid)?
- Intrinsic camera parameters for rendered views
- Ellipsoidal data generation
- Error running Pixel2Mesh in Google Colab: "python2: command not found" HOT 2
- Cannot interpret feed_dict error
- tf_nndistance_so.so not found HOT 2
- training problem
- Weighted chamfer loss and Weighted Edge Length Regularization
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 pixel2mesh.