Comments (8)
For "sparse" and "pose" mode, the landmarks are provided by
we return the vector points
which is of shape N, 2
, the coordinate z
is dropped in the tflite model.
However, for "dense" and "mesh" mode, we can get the landmarks via
as show in:
you need to hold the points[:, 2]
for getting coordinate z
from dense-head-pose-estimation.
感谢您的回答,意思就是"sparse" and "pose" mode估计出的特征点只是二维的吗?
如果想要得到三维坐标,就必须是"dense" and "mesh" mode?
from dense-head-pose-estimation.
"sparse" 和 "pose" 模式下的二维坐标也是通过三维坐标投影计算出来的
也就是说,tflite模型可以输出三维坐标,
但为了方便,现在上传的版本是二次封装后的,只能输出二维坐标
其实 "sparse" 和 "dense" 是没有区别的,都是从 3DMM 模型上按照一定规则采样几个点,
你完全可以通过对"dense"的结果 index pick 来得到 "sparse" 的三维坐标
from dense-head-pose-estimation.
好的,非常感谢!
from dense-head-pose-estimation.
抱歉再次打扰您
如何通过dense结果找到对应的sparse的68个点呢?也就是说如何知道"dense"中68个特征点的index呀?目前查找了一些资料,发现对dense facial landmark没有明确的编号。
from dense-head-pose-estimation.
您好,目前通过比较特征点的(x,y)坐标找到了对应的密集特征点的三维坐标。
但是目前仍有一个疑问就是这个Z坐标是深度值吗?我看了下结果,感觉不是相机到特征点的实际距离呀?
from dense-head-pose-estimation.
我建议参考 https://github.com/cleardusk/3DDFA_V2/blob/master/demo.ipynb 里面有能够渲染深度的demo
我们这两个repo实现的是同一篇论文,只不过我为了部署方便将BFM模型和后处理shape矩阵整合到tflite模型里了,而且由于我用不到z轴,所以模型里输出的z其实是未经过后处理的,你需要通过矩阵乘法将z轴还原到真实坐标,但我不建议这么做
如果你非要手动处理,我建议仔细看这个源码 来理解从模型输出线性变换到特征点(稠密、稀疏)的过程
from dense-head-pose-estimation.
我这两天参考了3DDFA_V2的代码也尝试跑了一下,不过发现他渲染深度得到的Z值不是相机到特征点的深度值,而是相对于空间中某个坐标系的Z值,不知道我的理解是否有误,还是说无法估计特征点距离相机的深度值?
from dense-head-pose-estimation.
Related Issues (15)
- request training code HOT 1
- the result of output of head pose
- asset/render.so: cannot open shared object file: No such file or director HOT 1
- Convert model to CoreML format HOT 1
- FLAME instead of BFM HOT 2
- MobileNet vs. ResNet HOT 1
- [Windows] git-bash can not generate render.so file HOT 1
- asset/render.so not found HOT 2
- there is no asset/render.so HOT 1
- __init__() got an unexpected keyword argument 'num_threads' HOT 2
- Landmark accuracy around the eyes. HOT 1
- How can i get Depth HOT 1
- Memory usage
- Where can I find the camera matrix params derived from the model for a given frame? HOT 2
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 dense-head-pose-estimation.