wbjang / code-nerf Goto Github PK

I want to reason on the pictures with unposed image, but​ i found that there are still some unfinished work in the open source code. I want to get the complete code and operation instructions.

Looking forwad to your reply.
Thank you!

Could you please release the code as soon as possible, i‘m very interseting in your work.Thanks!

Hi，
I am very interested in your work. After reading the article, I have a question: What method does CodeNeRF use to encode shape/texture, I think this part of the description in the article seems not clear enough

Looking forward to your answer!

After downloading the data, I'm not sure how to process it. I hope you can help me with this . Thank you!

Thanks for sharing such a great work!

I'm looking forward to the code release. It would be better if the code is implemented with PyTorch.

Thanks!

Hi,
I tried to optimize the camera pose jointly with shape and texture codes, where I set the azimuth and elevation as 0 and distance as 0.5 in the beginning, and add the parameters in the optimizer. However the result is still blurry after 500 iterations, I would like to ask if this is normal or I miss something in the steps?

Hi,

Thanks for the code release!

I was wondering if there are any pre-trained weights available?

Thanks,
Tom

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

Hello, Thank you for the nice work.
I am waiting for code publishing.
Could you tell me the estimated schedule?
It would help so much.

Thanks for the good research again.