Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Can't get the correct detailed mesh and image #83

Closed
QingXIA233 opened this issue Nov 4, 2021 · 9 comments
Closed

Can't get the correct detailed mesh and image #83

QingXIA233 opened this issue Nov 4, 2021 · 9 comments

Comments

@QingXIA233
Copy link

Hi, your work is really impressive! However, after I set everything properly and run the demo_reconstruct.py, I couldn't get the detailed mesh like what the README shows. I see other results like:
example1

But what I got is like:
16_vis_original_size

Everything is all right with the code, I tried both standard rasterization and pytorch3d rasterization, I also tried useTex(I got the required texture npz file) and without using it, but in each case, I got the same results like I show above. Does anyone know the reason here and maybe give me some hint to get the correct results? Thank you all, maybe this is a stupid question but it really is driving me crazy. :(

@Open-Debin
Copy link

Hello, I am also learn deca too. If you want to have a communication you can email me. michaeldbmeng19@outlook.com

@Natyen189
Copy link

This is exactly my issue right now too. Cant find what im missing tho

@cnpgs
Copy link

cnpgs commented Dec 1, 2021

Are you referring to the texture shown in the GIF? If so, I too have a similar issue.

I can get the .obj and .mtl files that can be opened with MeshLab, but the texture is only visible for the non-detailed shape (.obj) file; in other words, the .obj file with name '<file_name>_detail.obj' only has the shape visible, and no texture. Also, the texture is nowhere near as complete as that shown in GIF:

snapshot00

@birdflies
Copy link

@cnpgs I too have a similar issue. do you solve it?

@cnpgs
Copy link

cnpgs commented Dec 2, 2021

@cnpgs I too have a similar issue. do you solve it?

@birdflies No, unfortunately I have not solved it yet.

@qiliux
Copy link

qiliux commented Dec 8, 2021

I want to get the answer too..

@yfeng95
Copy link
Owner

yfeng95 commented Jan 6, 2022

Hi,

Thanks for pointing out this, it was a small bug in https://github.com/YadiraF/DECA/blob/f84855abf9f6956fb79f3588258621b363fa282c/decalib/deca.py#L304,
I forgot to add color before.
Just fixed this, should work now, thanks!

@yfeng95 yfeng95 closed this as completed Jan 6, 2022
@goldwater668
Copy link

@yfeng95 Tried the latest code, still did not solve the problem mentioned above

@yaozhuyu-nreal
Copy link

@yfeng95 Tried the latest code, still did not solve the problem mentioned above
https://github.com/yfeng95/DECA/blob/master/decalib/deca.py#L309, replacing dense_colors with dense_colors/255 will work.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

9 participants