neuralSubdiv
neuralSubdiv copied to clipboard
HTDerekLiu
tosca shape
Hi, I am trying to subdivide the shapes in the Tosca dataset, as shown in Table 2 in the paper, but I found that many of the shapes have boundaries, how did you subdivide these shapes and get the results?
In addition, the Metro tool outputs two mean distances, which is used as the average surface distance
Re: TOSCA I closed the mesh (see attached). Alternatively, you could make it work by doing some padding too. tosca_closed.zip
Re: Metro Sorry it has been a while, I couldn't recall what are the numbers and which one I used.
Re: TOSCA I closed the mesh (see attached). Alternatively, you could make it work by doing some padding too. tosca_closed.zip
Re: Metro Sorry it has been a while, I couldn't recall what are the numbers and which one I used.
I'm sorry, but I might have one more question for you. I performed mesh simplification on the original meshes you shared, then subdivided them with neural subdivision, and finally quantitative analysis with Metro tools, but got poor results on some models. and I have observed that the simplified mesh model is a little bad, so could you please share your simplified mesh?
Or am I using the Metro tool incorrectly? I used the simplest assessment, "Metro A.obj B.obj."
Based on the file name, this should be the ones I was using (not 100% sure, it has been a while)
- tosca test data: https://drive.google.com/file/d/1BKbFRmXMToMMr0o6zr1j3AYbAruuOcLD/view?usp=drive_link
- tosca train data: https://drive.google.com/file/d/1hYR-MtOmNiXyE6I5cUQgrm55twCeXcpI/view?usp=drive_link
Based on the file name, this should be the ones I was using (not 100% sure, it has been a while)
- tosca test data: https://drive.google.com/file/d/1BKbFRmXMToMMr0o6zr1j3AYbAruuOcLD/view?usp=drive_link
- tosca train data: https://drive.google.com/file/d/1hYR-MtOmNiXyE6I5cUQgrm55twCeXcpI/view?usp=drive_link
Thanks for sharing, but it seems to require additional permissions to access this connection
Based on the file name, this should be the ones I was using (not 100% sure, it has been a while)
- tosca test data: https://drive.google.com/file/d/1BKbFRmXMToMMr0o6zr1j3AYbAruuOcLD/view?usp=drive_link
- tosca train data: https://drive.google.com/file/d/1hYR-MtOmNiXyE6I5cUQgrm55twCeXcpI/view?usp=drive_link
I used the coarse mesh you provided and subdivided it by neural subdivision, but the Hausdorff distance calculated by Metro between the prediction model and the ground-truth model of cat is still 134.xxxx >>>2.08 (the figure in paper ). However, when I work with other models, non-TOSCA models, the values are normal.Is there a problem with the model of the Tosca dataset？Or am I using the Metro tool incorrectly?
I guess the mesh scale may be incorrect? Here are some pre-trained weights on centaur and subdivision results for you to debug. https://drive.google.com/file/d/197Nm5Z6uI6uHmf-xWXWH0ljXrUuwobzk/view?usp=sharing
I guess the mesh scale may be incorrect? Here are some pre-trained weights on centaur and subdivision results for you to debug. https://drive.google.com/file/d/197Nm5Z6uI6uHmf-xWXWH0ljXrUuwobzk/view?usp=sharing
You are right, it is a matter of scale, but how to adjust the scale correctly?
I guess the mesh scale may be incorrect? Here are some pre-trained weights on centaur and subdivision results for you to debug. https://drive.google.com/file/d/197Nm5Z6uI6uHmf-xWXWH0ljXrUuwobzk/view?usp=sharing
And I'm a little confused, why is there such a big difference between the scale of subdivision output mesh and the ground-truth mesh？
The method is not scale invariant so we normalize the mesh to a unit box. In the previous data, *_s0.obj, *_s1.obj, *_s2.obj are the subdivision results. *_target.obj are the target ground truth shapes used to compute losses.
Hello, I would like to raise a question about bijective mappings in Successive self-parameterization. When establishing the mapping g from subdivision mesh to coarse mesh, why use the barycentric coordinates to encode the mapping relationship instead of directly using the midpoint interpolation method to represent the mapping relationship?
We estimate the mapping between the subdivided mesh and the coarse mesh using exactly the idea you mentioned -- the mid point relationship. The barycentric coordinates is used to represent the mapping between the input high resolution mesh and the coarse mesh.