Comments (3)
Good question,
A common technique is to use marching cubes. We observed it doesn't work so well.
Furthermore, coloring the mesh from the radiance field is not as simple as querying the radiance field at vertices, as pixel values are computed by integrating over an entire ray.
If you still want to give it a try you can probably use the implementation with MC from Stable dreamfusion
from latent-nerf.
@galmetzer Hi, I am trying to migrate the export_mesh
implementation in Stable Dreamfusion to this project. However, I got the right geometry of the mesh but wrong albedo texture like this. Do you know why it happened?
from latent-nerf.
hi I tried to use stable dreamfusion's export_mesh function with shape-guided NeRF generation here, but the output mesh doesn't make sense. May I ask did you run this on shape-guided NeRF or unconstrained NeRF?
from latent-nerf.
Related Issues (20)
- Missing High frequency details
- Orientation loss
- How to finetune the model from latent type?
- The "teddy" sketch shape cannot be loaded properly
- command to run Textual Inversion HOT 1
- TypeError: grid_encode_forward(): incompatible function arguments. HOT 1
- Training Cost
- The results like yellow clouds HOT 5
- Conda environment HOT 5
- when is google collab going to be released
- Some doubts about using rgb and rgbrefinement HOT 1
- Could you provide the hyperparameters to reproduce the results of latent-nerf in the readme? HOT 4
- Question about shading HOT 1
- Is the setting of learning rate sensitive?
- Get strange result
- CUDA out of memory issue HOT 3
- High resolution problems.
- How to modify nerf_dataset.py to fit my data? HOT 1
- Reproducing the german shepherd example
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 latent-nerf.