Comments (5)
Okay, I get it. Thank you very much for your patient reply!
from ostec.
Can you give me more insight about at which part you had this problem? Or maybe share the generated assets?
from ostec.
self.tcoords_full = mio.import_pickle('models/topology/tcoords_full.pkl')
self.tcoords = mio.import_pickle('models/topology/tcoords.pkl')
self.mask = mio.import_pickle('models/topology/mask_full2crop.pkl')
self.tight_mask = mio.import_pickle('models/topology/mask_full2tightcrop.pkl')
self.template = mio.import_pickle('models/topology/all_all_all_crop_mean.pkl')
self.lms_ind = mio.import_pickle('models/topology/all_all_all_lands_ids.pkl')
Thank you for your reply. I found that when I use 3D vertices in tcoords_full.pkl
to generate obj files, the texture and geometry are not aligned. When I use tcoords.pkl
and mask_full2crop.pkl
to generate obj, the texture and geometry are aligned, but the texture of the ears are not included. Can you explain the role of these files? Or how to generate obj files containing ears?
in short, this code can be used to generate obj aligned with texture and geometry:
self.full_uv_vertices = self.tcoords_full.copy().points
self.full_uv_vertices[self.mask] = self.tcoords.points
Using the following code alone generates misaligned:
self.full_uv_vertices = self.tcoords_full.copy().points
from ostec.
You are right. The Full topology is different than the topology of the UV texture images OSTeC is generating. The reason why I preferred to exclude ears is that they are often occluded in StyleGAN space and are difficult to match correctly. Thus you need to use cropped topology to visualize properly.
from ostec.
Okay, I get it. Thank you very much for your patient reply!
hello,i face the same problem.how do you fix it?
from ostec.
Related Issues (20)
- How to obtain the visibility mask of the raw face image HOT 2
- How to render correctly? HOT 3
- Unable to reproduce paper results HOT 3
- Render 4-channel image? HOT 2
- Download failed, there are other download paths? HOT 5
- I would like to know how to get the de-occluded frontal face image HOT 2
- Crashing while running the program: same configuration that this repository was tested with HOT 1
- UV map and mesh do not match HOT 1
- my textured UV is different from the one in paper HOT 5
- Will the repository work with CUDA 11? HOT 7
- Why dense landmarks need to minus 5?
- args parameters HOT 1
- nvcc fatal : Host compiler targets unsupported OS.
- IndexError: index 0 is out of bounds for axis 0 with size 0` HOT 2
- Error in conda environment HOT 1
- Training Step
- run parameter -f unrecognized
- texture and shape are not aligned
- i get ResolvePackageNotFound:error i'm trying on Windows
- tensorflow_core/include/Eigen/Core:28:12: fatal error: cuda/std/complex: No such file or directory
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 ostec.