Comments (5)
Hi, Thanks for trying out our code and for this amazing enhancement!
- Please open a pull request and feel free to add an example use of the
.ply
format on the README. Happy to incorporate it ourselves if you think that's better. - Yes, we currently use isotropic scaling. It should be easy for us to support anisotropic Gaussians in Pytorch (we need to add a few configs across the code, adding back our old code). I'll add this to our V2 list. We don't see any performance discrepancies for isotropic vs anisotropic. The nice thing about isotropic is that it has fewer parameters, so if we implement the CUDA operations accordingly, it should be faster and have lower memory. Hopefully, we plan to have custom CUDA implementations soon.
from splatam.
Thank you for your thoughtful consideration. I have opened a pull request. #29
By drag and dropping .ply
file generated in the same directory as params.npz
into any GS viewers, for example, https://playcanvas.com/super-splat you will visualize / edit the Gaussians generated by your algorithm.
from splatam.
Hi, Thanks for trying out our code and for this amazing enhancement!
- Please open a pull request and feel free to add an example use of the
.ply
format on the README. Happy to incorporate it ourselves if you think that's better.- Yes, we currently use isotropic scaling. It should be easy for us to support anisotropic Gaussians in Pytorch (we need to add a few configs across the code, adding back our old code). I'll add this to our V2 list. We don't see any performance discrepancies for isotropic vs anisotropic. The nice thing about isotropic is that it has fewer parameters, so if we implement the CUDA operations accordingly, it should be faster and have lower memory. Hopefully, we plan to have custom CUDA implementations soon.
Hey, thank you for your work. I am reading the code these days. I want to know how do you imply isotropic in code. Is that because you use torch.tile() to copy scale? So that all three directions' scales will have the same grad?
from splatam.
Hi, Yes. Since the Gaussians are isotropic (spherical), we only model one parameter for scale across x, y & z instead of using 3 parameters.
As you mentioned, currently, we pass the Gaussians using a tile operation to be compatible with the anisotropic CUDA rendering from the official 3DGS code, as shown here:
Line 112 in bbaf5cc
Furthermore, the isotropic Gaussians are defined here:
Line 141 in bbaf5cc
from splatam.
@Nik-V9 I got it. Thanks!
from splatam.
Related Issues (20)
- Question regarding the necessity of viewing cameras and relative pose transformations HOT 1
- Error installing rasterizer [warning: GCC] HOT 1
- Error when running SplaTAM on Scannet++ dataset HOT 2
- Rendering data with very near depth (< 0.2 m) [Duplicate] HOT 2
- Training with a live streaming HOT 1
- `RuntimeError: numel: integer multiplication overflow` HOT 3
- How to create a new dataset HOT 1
- Query regarding constant camera intrinsics HOT 8
- Type of Loss Function HOT 2
- GPU memory during training HOT 1
- Query regarding first camera pose HOT 2
- Query regarding Scannet dataset config HOT 2
- Query regarding data loading for custom dataset HOT 3
- Question about the evaluation metrics
- Query regarding Replica Dataset Version & Performance HOT 3
- Question regarding number of frames tracked during SLAM HOT 1
- Inquiry Regarding Runtime Discrepancies in Splatam HOT 4
- Why is the projmatrix in cam the same to first frame? HOT 4
- Graphics card memory usage
- Query regarding Depth Backward Pass (Duplicate) 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 splatam.