Anh Tran

Look like CMake could not find OpenCV library, making your docker failed to build the C++ code to generate the executable file TestBump. I plan to develop a Python-only version,...

I used OpenCV 2 when developing this code. I think it is not hard to adapt it to OpenCV 3. See an example pull request in a similar project: https://github.com/anhttran/3dmm_cnn/pull/45

Dear, One simple solution is to disable cudnn in the main code: `torch.backends.cudnn.enabled = False` Hope it help. Best regards, Anh

I plan to develop a Python-only version, but I am quite busy with my current schedule. I may release it some time in June.

Dear, The slowest part was symmetry-based model completion. If you are OK with incomplete 3D models, the early modules can be optimized for real-time.

Dear all, In case you have an issue of compiling my code, I have updated the CMakeLists.txt of CvGL and added Docker support. Please check the updated README for more...

You can find the instructions in README.md. Best, Anh

Dear all, In case you have an issue of compiling my code, I have updated the CMakeLists.txt of CvGL and added Docker support. Please check the updated README for more...

Dear, You can use **iris3d_file.sh** to model a single image or **iris3d_dir.sh** to model images inside a folder. You can edit the input/output paths inside these scripts. The output folder...

My model is computed on the face crop (.ply_cropped.png). It uses 3DMM from BaselFaceModel, with estimated shape parameters, texture, and expression parameters stored in (.alpha), (.beta), and (.expr) files. The...