Deep3DFaceReconstruction icon indicating copy to clipboard operation
Deep3DFaceReconstruction copied to clipboard

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019)

Results 99 Deep3DFaceReconstruction issues
Sort by recently updated
recently updated
newest added

When i am running the python demo.py command below error is encountered. ![demopy](https://user-images.githubusercontent.com/76882094/110216828-407e0080-7ed7-11eb-99df-bf09541c744c.png) FailedPreconditionError (see above for traceback): Attempting to use uninitialized value resnet_v1_50/block1/unit_3/bottleneck_v1/conv3/weights [[node resnet_v1_50/block1/unit_3/bottleneck_v1/conv3/weights/read (defined at /home/preksh/tf_mesh_renderer/Deep3DFaceReconstruction/networks.py:14) ]]

Can you please explain the below step for The expression basis are constructed using Facewarehouse data and transferred to BFM topology.

When I plot landmarks_2d on an image in input folder, it produces bad result. Why is this happening? ![vd005](https://user-images.githubusercontent.com/6318995/58154391-77f0ce00-7cac-11e9-83b9-947e3d6f2426.png) ![vd092](https://user-images.githubusercontent.com/6318995/58154410-7f17dc00-7cac-11e9-9b54-326720493f48.png) ![vd034](https://user-images.githubusercontent.com/6318995/58154416-8212cc80-7cac-11e9-882b-bdb884e03431.png)

python=3.6 , tensorflow=1.12, cuda=9.0 I used 'pip install mesh_renderer' to install mesh_renderer. Did anyone meet with this problem when import the mesh_renderer? ![image](https://user-images.githubusercontent.com/38290717/90329702-a9546880-dfd9-11ea-929b-d4d275cba842.png)

After launching demo and visualization recon_img I got only grey contour of the face and some trace of the mouth. All other stuff works well, thank you!

Hi,thanks for your work, I am really interested ! Now I have implement training process according to your paper, but I found some problems during training: 1. Image-level loss is...

My 5 landmarks come from GT and use pre-trained model FaceReconModel.pb, but they are far from the author's performance. why?Is there any way to improve?Thank you~ ![image](https://user-images.githubusercontent.com/19618093/102440081-835bd500-405a-11eb-9e29-bf671cc267f0.png)

I run the demo successfully,but the result don not contain the texture file. so how to get the texture file,and how to generate the result as paper(readme)? thx

Hi, I'm a new comer in deep learning. Just want to try this project but I got an error. Do I have to install Matlab to run this code? As...