junshengzhou / levelsetudf Goto Github PK

Thank you for your excellent work. I have tried both the demo and scene modes using the object.conf and scene.conf files. However, the normal consistency of the results in the outs/{modelname}/mesh directory does not seem to be very good. Is there anything wrong?
I would appreciate it if you could explain how the NC metric is calculated.

demo:

scene0001

Thank you for outstanding work!
Specifically, I am interested in the settings used for KITTI scene. Can you share the details of experimental settings?
Thank you!

Hello!
你在你们的工作中有提到：”The differential networks struggle from learning the zero level set where the UDF is not differentiable, which leads to large errors on unsigned distances and gradients around the zero level set, resulting in highly fragmented and discontinuous surfaces. However, the non-zero level sets are much smoother and more continuous than the zero level set.“
我想询问一下：

1. 为什么zero level set的UDF场是不可微的？
2. 为什么non-zero level sets的UDF场是可微的呢？

Query data not found. Processing data...
Traceback (most recent call last):
File "run.py", line 286, in
runner = Runner(args, args.conf)
File "run.py", line 70, in init
self.dataset = Dataset(self.conf['dataset'], args.dataname)
File "/data/LevelSetUDF-main/models/dataset.py", line 96, in init
self.object_bbox_min = np.array([np.min(self.point[:,0]), np.min(self.point[:,1]), np.min(self.point[:,2])]) -0.05
File "<array_function internals>", line 200, in amin
File "/root/anaconda3/envs/levelsetudf/lib/python3.8/site-packages/numpy/core/fromnumeric.py", line 2946, in amin
return _wrapreduction(a, np.minimum, 'min', axis, None, out,
File "/root/anaconda3/envs/levelsetudf/lib/python3.8/site-packages/numpy/core/fromnumeric.py", line 86, in _wrapreduction
return ufunc.reduce(obj, axis, dtype, out, **passkwargs)
ValueError: zero-size array to reduction operation minimum which has no identity

ValueError: zero-size array to reduction operation minimum which has no identity

fantastic job！when will you release the source code？