Comments (6)
Hi, many thanks for your interest in our work:)
You can tweak the code here to not set the initialized 3D Gaussian Splatting position on SMPL-X mesh, but on the customized mesh like pot or vase you mentioned, or use text-to-point-cloud prior like Point-E and Shap-E for initialization. The function inherited from GaussianDreamer gives an example of Shap-E initialization. Also, note that since general object like pot or vase may not have a clearly defined skeleton, the guidance should also be changed to an uncondition SD accordingly.
Best,
from humangaussian.
Hi @alvinliu0
Does tweaking code in that part does the work?
Cause in the configure definition i see a initialization of skeleton SMPLX as given below.
from humangaussian.
from humangaussian.
Because the actual part for 3DGS point cloud initialization is here. So if you want to change to shap-e initialization, you can comment off those part of code and turn on shap-e part.
from humangaussian.
Hi @alvinliu0
I have uncommented this shap-e initialization and got decent results. But if I need to use prior like SMAL, 3DGS point cloud initialization does work or should I be creating a separate skeleton class for the prior shape under consideration?
from humangaussian.
Yes, because there's no strict alignment between prior like Shap-E or Point-E with body skeleton (you can not even guarantee that the 3d human generated by them are correct or complete). Hence it might be difficult to use them as prior/initialization while still use skeleton as condition for ControlNet or our texture-structure joint model as SDS.
from humangaussian.
Related Issues (20)
- wierd operation when running launch.py HOT 8
- lauch init takes too long to finish HOT 4
- render animation w/o gui HOT 2
- AMD GPU HOT 1
- ๆฅ้self.dataset = self.trainer.val_dataloaders.dataset error 'list' object has no attribute 'dataset' HOT 6
- There is a problem trying to resume the model HOT 1
- Questions about training the Texture-Structure Joint Model HOT 1
- Why the size of avatars are the almost same?? HOT 2
- Why the skeleton image and the image rendered by gassian are in different camera view? HOT 3
- Why Error RuntimeError: expected scalar type Float but found Double ???
- Clarification on Size-Conditioned Gaussian Pruning HOT 1
- CUDA out of memory
- customized text prompt HOT 1
- cuda issues HOT 13
- An error was reported while training the model with two 3090.
- How to generate smpl-xl coefficients to animinate the humangaussian? HOT 1
- RuntimeError: Input type (torch.cuda.HalfTensor) and weight type (torch.HalfTensor) should be the same HOT 6
- About use sds loss without anpg
- About the noise_pred calculation in sds loss in dual_branch_guidance.py
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from humangaussian.