nv-tlabs / deftet Goto Github PK

Is the code will be delayed.?

Hi, I am just wondering approximately when the code may be available.

Hi,
Thanks for your great work!
I am wondering when you will release the 2D supervision training code?
Thanks!

Hello,

I see that last 4 issues with the request of code sharing hasn't been answered. Is the code gonna be available soon or it's not planned at all?

Thanks.

Hi, thank you for your excellent work. And I'm wondering when the code will be released?

Running python train_multigpu.py .... indicate error:

Traceback (most recent call last):
File "train_multigpu.py", line 10, in
from layers.DefTet.deftet import DefTet
File "/home/jiangpin/DefTet/layers/DefTet/deftet.py", line 12, in
from utils import tet_utils
File "/home/jiangpin/DefTet/utils/tet_utils.py", line 15, in
from utils.lib.tet_point_adj.interface import Tet_point_adj
ModuleNotFoundError: No module named 'utils.lib'

No dependent libs found when installation :

HOME_DIR="$PWD"
cd "$HOME_DIR/utils/lib/tet_adj_share"
bash do_all.sh
cd "$HOME_DIR/utils/lib/tet_face_adj"
bash do_all.sh
cd "$HOME_DIR/utils/lib/tet_point_adj"
bash do_all.sh
cd "$HOME_DIR/utils/lib/colaps_v"
bash do_all.sh
cd $HOME_DIR

Dear DMTet group, 

Thank you for your great work of DMTet and DefTet!

I am a PhD student in China, and want to follow Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis(DMTet). I'm trying to modify the codebase of DefTet to achieve the TSDF supervision and volume subdivision claimed in DMTet. 

However, a problem confused me for a while.  The DMTet paper claimed:

'We first identify surface tetrahedra Tsurf  based on the current s(v) value. We then build a graph G = (Vsurf; Esurf), where Vsurf; Esurf correspond to the vertices and edges in Tsurf.'  

I've read DefTet and Kaolin carefully, including kaolin.ops.conversions.marching_tetrahedra(). But different meshes have different numbers of surface tetrahedra Tsurf. I was wondering how the meshes with different Tsurf can be synthesized in one batch, and how the different graphs G can be used in one forward process. 

So I sincerely hope to get help from you. Thanks for your great work again!

On DefTet paper, there is a section that compare DEFTET with DIB-R, DVR, and FIXEDTET. May I know whether the training script will be released in the near future?

Hello, thank you for the great work! I was trying to run training script but it takes a long time to preprocess data every time even though it is cached the first time. Are we expecting the kaolin io.dataset call to just load in cache every time or does it not do that?

Hi, I am just wondering approximately when the code may be available.