qiujiedong/laplacian2mesh

Laplacian2Mesh: Laplacian-Based Mesh Understanding

Hi there 👋

My name is Qiujie Dong, a Ph.D. candidate in computer science.

• 🔭 I’m currently working at the School of Computer Science and Technology, Shandong University.
• 🌱 I’m currently learning computer graphics via deep learning.

laplacian2mesh's Issues

igl安装问题

在Ubuntu系统上进行配置环境
pip install ig
l报错:ERROR: Could not find a version that satisfies the requirement igl (from versions: none)
ERROR: No matching distribution found for igl
然后问gpt,说需要安装cmake和eigencmake安装比较顺利pip直接安装即可,
但是eigen一直搞不明白如何安装，
直接将其克隆到当前项目中了,但不知道如何config.

When are you planning to release the source code?

Congratulations for the paper!
When are you planning to release the source code?

Error using Linux env

pre-trained models?

Thanks for sharing the source code! Is it also possible to share pre-trained model weights?

Pre-processing error attempting to run code on Windows 10

Hello!

I am trying to run the code that pre-processes the coseg_aliens dataset and coming up with this error message:

------generate vertices ground truth from edges------
data/coseg_aliens\train\1.obj
Traceback (most recent call last):
File "./prepare/pre_seg_dataset.py", line 317, in
generate_vertices_ground_truth_from_edges(args)
File "./prepare/pre_seg_dataset.py", line 211, in generate_vertices_ground_truth_from_edges
meshcnn_mesh = Mesh(os.path.join(subset_mesh_path, file), opt)
File "C:\Users*\PycharmProjects\Laplacian2Mesh\prepare\mesh.py", line 441, in init
fill_mesh(self, file, opt)
File "C:\Users*\PycharmProjects\Laplacian2Mesh\prepare\mesh.py", line 24, in fill_mesh
mesh2fill.ve = mesh_data['ve']
File "C:\Users*****\AppData\Local\anaconda3\envs\L2M2\lib\site-packages\numpy\lib\npyio.py", line 260, in getitem
raise KeyError("%s is not a file in the archive" % key)
KeyError: 've is not a file in the archive'

Have you ever seen this before? It's just your vanilla code that is running, I have not made any modifications.

Using sparse matrices

Hi,

I'm working with meshes with 80k-100k vertices.
Preprocessing them requires a lot of memory, are you planning to use sparse matrices instead?
I can open a pull request if you're interested bc I've modified the code already.

Daniel

Access to Wandb

Hi,

As I've been trying to train and replicate the same result as yours based on the code provided I was directed to Wandb to visualize the results but I would get this error that I do not have sufficient permission to do so, I was wondering if this is possible that the permission would be granted or maybe you could walk me through it whether I can do it myself and generate my own Wandb because I am not very familiar with Wandb tool.
Thank you