VAST-AI-Research / TripoSR

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

increase the Marching Cubes Resolution above 320

ezequielal39 opened this issue · comments

Is it possible to increase the Marching Cubes Resolution above 320 by changing the variable "maximum = 320" in the file "gradio_app.py"? Or would it cause an error?

#44 (comment)

Yes. It appears that torchmcubes doesn't support resolutions higher than a certain limit.

I fixed this, you can try #68

@thatname impressive speedup! One thing I noticed, models have checker/square pattern which seems to be invariant to resolution or chunk size (arguments in the run.py). Do you know if it's due to something .cu file of marchingcubes? Or some hard-coded value.

I counted them and the value seems to be exactly 32 vertically.

image

@thatname impressive speedup! One thing I noticed, models have checker/square pattern which seems to be invariant to resolution or chunk size (arguments in the run.py). Do you know if it's due to something .cu file of marchingcubes? Or some hard-coded value.

I counted them and the value seems to be exactly 32 vertically.

image

I think it's limited by the underlying triplane resolution, which is 64.

@thatname impressive speedup! One thing I noticed, models have checker/square pattern which seems to be invariant to resolution or chunk size (arguments in the run.py). Do you know if it's due to something .cu file of marchingcubes? Or some hard-coded value.
I counted them and the value seems to be exactly 32 vertically.
image

I think it's limited by the underlying triplane resolution, which is 64.

Did you try different normal smoothing? Could help hide the janky marching cube faces.

image

See there better normal smoothing helps a lot

@thatname impressive speedup! One thing I noticed, models have checker/square pattern which seems to be invariant to resolution or chunk size (arguments in the run.py). Do you know if it's due to something .cu file of marchingcubes? Or some hard-coded value.
I counted them and the value seems to be exactly 32 vertically.
image

I think it's limited by the underlying triplane resolution, which is 64.

Did you try different normal smoothing? Could help hide the janky marching cube faces.

image

See there better normal smoothing helps a lot
@mrbid Can you give more details about normal smoothing, I am gonna do similar stuff. Which method do you use?

@thatname impressive speedup! One thing I noticed, models have checker/square pattern which seems to be invariant to resolution or chunk size (arguments in the run.py). Do you know if it's due to something .cu file of marchingcubes? Or some hard-coded value.
I counted them and the value seems to be exactly 32 vertically.
image

I think it's limited by the underlying triplane resolution, which is 64.

Did you try different normal smoothing? Could help hide the janky marching cube faces.
image
See there better normal smoothing helps a lot
@mrbid Can you give more details about normal smoothing, I am gonna do similar stuff. Which method do you use?

Yeah in Blender for example the more times you apply the smooth normals the smoother the normals become, you can apply it a few times it's basically like a gaussian blur on the vertex normals which dictate how light reflects off the faces.

Peek.2024-05-13.22-12.mp4

More information about showing vertex normals in Blender:
https://www.katsbits.com/codex/show-normals/