How to optimize and estimate the camera pose

[dachengxiaocheng]

Hello,

Thank you very much for the code release!

Refer to the paper "codeNeRF", I find the camera pose, shape and texture code are jointly optimized during testing/inference.

But in the open-source file "optimizer.py" (the function "optimize_objs"), it seems that the ground truth camera pose is used directly and only the shape and texture code are optimized.

Do I miss something or misunderstanding the code?

Thank you so much.

Best

[yushengjiexy]

hi,i have the same problem.It seems that the writer has not released this code.If you get the code, could you give me a copy? thank you! My email:[email protected]