Hi, I really appreciate your greate work!

An error occurred when i run the "generate_depth.py", how do i solve it?

: ~/unsupervised3dhuman-main$ python generate_depth.py --filename ./demo/demo_depth/shortshort_flying_eagle.000075_depth.ply --gender male Traceback (most recent call last): File "generate_depth.py", line 18, in from src.utils import index_points, farthest_point_sample File "/home/iot/PycharmProjects/unsupervised3dhuman-main/src/utils.py", line 7, in from pytorch3d import _C ImportError: libc10_cuda.so: cannot open shared object file: No such file or directory

I create an anaconda environment according your "environment.yaml", the system is ubuntu18.04 and cuda10.2

Thank you!

Hi.

I'd like to start thanking you, because I was looking for solutions on how to fit a point cloud for animation reasons, and your work is the best I could find on the topic, it is very close to what I'm trying to do and you published some code, so thank you so much for your effort.

Sorry to disturb you, but I was experimenting with your algorithm on body scans, and I came across some issues. I am talking about body facing direction, legs crossing and body parts compenetration.

I see that in previous issues you already solved these issues, but it is not working for me.

I added the row -- pred_pose[0, 1] = (pred_pose[0, 1] + 1.57).unsqueeze(0).float() after line 100, but it is still not working I suspected the reason could be in the fact that my body is oriented along a different axis, but the model actually predicts the orientation correctly, it just places the body rotated 180 degrees (face towards the back of the original point cloud). This creates a pose estimation that is completely wrong. I am working on point clouds of various people in a slight A-pose, so I guess it should be a very easy task, so it is the only explanation for those weird poses generated.

Any suggestion for this? Should I apply rotations to my original point cloud in advance? Am I doing something wrong? I was trying to make your code work before trying and training my own solution.

About leg crossing, I saw you applied another correction, but the issue is in a language I don't understand, so it is difficult for me to understand if it has been already patched, or where should I change the code.

I don't know if you are still working on this, and if you can help me, but I would be very grateful if you could find a minute to drop me some hints

Thank you in advance for your consideration and your help

Have a nice day

你好，请原谅我英文不太好，怕表达的不清晰，就用中文说了。 我测试了您的网络。用的是FAUST的扫描模型。 请问是需要对这里的扫描模型进行预处理么？我直接用的话，得到的结果好像有些差，还是说我的环境有什么问题，我直接用的readme上的提示做的，创建的虚拟环境。 这是我的结果 分别对应的scans中的096和035. 希望能得到您的帮助，不胜感激

Hi,

I ran the demo you provdied for fitting the SMPL model onto a partial scan:

python generate_depth.py --filename ./demo/demo_depth/shortshort_flying_eagle.000075_depth.ply --gender male

but the surface_EM_depth minimization outpus NaN s for the demo example you provided. Does the code work for you?

Thanks in advance, David

Hi,

could you specify which subjects and frames did you use to evaluate the methods on the CAPE and CMU datasets (Table 1 and 2 from the paper) ?

Thank you in advance.

Hi, Wang sen, I am not very familiar with point cloud processing, I don't know how to convert depth image with camera intrinsic parameters to ply file, could you help me, thank you.