Comments (4)
That is because when the authors compute the shape, they discard the mean expression from 01_MorphableModel.mat, but do not use the counterpart in Exp_Pca.bin.
from deep3dfacerecon_pytorch.
您好,我注意到您源码里训练时用的BFM model是经过转化以后只有35709个点的BFM model
我根据'BFM_exp_idx.mat'从原始BFM09(有53490个顶点)中提取了53215个点并且与“Exp_Pca.bin"中的表情基进行了整合,最终得到了'bfm_53215.mat'(相对于您用的35709个点的模型,增加了脖子和耳朵,验证过其拓扑结构也没有问题)。
我注意到您在根据回归出来的coeff来重建出个性化人脸模型时,进行了recenter,具体如下(详情可见/model/bfm.py):
想问若我想使用我得到的'bfm_53215.mat'来重建出含有脖子和耳朵的个性化人脸模型,是否也需要recenter?
若recenter以后,在相同的coeff情况下,得到的含有脖子和耳朵的人脸模型再去掉脖子和耳朵以后 跟 直接将coeff作用于35709个点的BFM model得到的个性化人脸模型,他们的三维点坐标是不一样的。我个人认为的原因是在recenter是求平均值时,因为bfm_53215的meanshape的平均值与bfm_35709的meanshape的平均值不同。
recenter的目的是为将人脸的中心改为(0, 0, 0),我们训练的网络的pose是基于“bfm_35709”的空间位置预测得到,所以将回归得到的系数直接用于“bfm_53215”,会出现pose不一致的问题,解决办法也较为直接,即利用“ bfm_53215”减去“bfm_35709”的中心即可。
from deep3dfacerecon_pytorch.
您好,我注意到您源码里训练时用的BFM model是经过转化以后只有35709个点的BFM model
我根据'BFM_exp_idx.mat'从原始BFM09(有53490个顶点)中提取了53215个点并且与“Exp_Pca.bin"中的表情基进行了整合,最终得到了'bfm_53215.mat'(相对于您用的35709个点的模型,增加了脖子和耳朵,验证过其拓扑结构也没有问题)。
我注意到您在根据回归出来的coeff来重建出个性化人脸模型时,进行了recenter,具体如下(详情可见/model/bfm.py):
想问若我想使用我得到的'bfm_53215.mat'来重建出含有脖子和耳朵的个性化人脸模型,是否也需要recenter?
若recenter以后,在相同的coeff情况下,得到的含有脖子和耳朵的人脸模型再去掉脖子和耳朵以后 跟 直接将coeff作用于35709个点的BFM model得到的个性化人脸模型,他们的三维点坐标是不一样的。我个人认为的原因是在recenter是求平均值时,因为bfm_53215的meanshape的平均值与bfm_35709的meanshape的平均值不同。
您好,我遇到了同样的问题,可否发我一下您生成的bfm_53215.mat来作为参考和验证
from deep3dfacerecon_pytorch.
您好, 请问,我可否进一步缩减BFM model的顶点数,来训练获取一个顶点数更少的人脸模型结果? 谢谢
from deep3dfacerecon_pytorch.
Related Issues (20)
- RuntimeError: Cuda error: 304[cudaGraphicsGLRegisterBuffer(&s.cudaPosBuffer, s.glPosBuffer, cudaGraphicsRegisterFlagsWriteDiscard);] HOT 1
- ValueError: Unknown CUDA arch (8.9) or GPU not supported
- On the issue of differences in training visualization and testing effectiveness
- False error in training
- FileNotFoundError: [Errno 2] No such file or directory: './checkpoints/face_recon/epoch_latest.pth'
- Use this project with recent GPU ? HOT 6
- Open mouth HOT 2
- A little confusion about mask used for computing feat loss HOT 1
- Pretrained model
- No module named 'models.arcface_torch' HOT 1
- RuntimeError: CUDA error: no kernel image is available for execution on the device
- ImportError: DLL load failed HOT 2
- RuntimeError: Error building extension 'nvdiffrast_plugin_gl': ninja: error: build.ninja:3: lexing error HOT 1
- What does align_img do in test.py? HOT 1
- error while running
- UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd3 in position 1454: invalid continuation byte
- ImportError: libtorch_cpu.so: undefined symbol: iJIT_IsProfilingActive HOT 5
- resnet50-0676ba61.pth
- Thank you for your work. There is no result showing in preprocess_in_th_wild.py
- Requirements for topology files
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 deep3dfacerecon_pytorch.