About using xatlas to extract uvmap

[jugwangjin]

Hi.
Thank you for great work.

While I was working on this work, I found out that the resulting uv map is corrupted.

I fount that although xatlas duplicates some vertices, current work does not apply this on the mesh class.

the resulting uv map is

however,

if I add two lines in the xatlas_uvmap a bit, like

@torch.no_grad()
def xatlas_uvmap(self):
    import numpy as np
    # Create uvs with xatlas
    v_pos = self.vertices.detach().cpu().numpy()
    t_pos_idx = self.indices.detach().cpu().numpy()
    vmapping, indices, uvs = xatlas.parametrize(v_pos, t_pos_idx)

    # Convert to tensors
    indices_int64 = indices.astype(np.uint64, casting='same_kind').view(np.int64)
    vmapping_int64 = vmapping.astype(np.uint64, casting='same_kind').view(np.int64)
    vmapping = torch.tensor(vmapping_int64, dtype=torch.int64, device=self.device)

    uvs = torch.tensor(uvs, dtype=torch.float32, device=self.device)
    faces = torch.tensor(indices_int64, dtype=torch.int64, device=self.device)

    self._uv_coords = uvs
    self._uv_idx = faces
    self.vmapping = vmapping

    # ADDED LINES
    self.vertices = self.vertices[vmapping]
    self.indices = faces

the resulting UV map goes

It may not affect the result, hope it helps.
especially about the tangent computation, which includes uv coordinates.

[sbharadwajj]

Hi,

Thank you so much for your input! Let me recheck.

As far as I remember, I have verified the UV coordinates in the original code, but a bug might have been introduced when I was cleaning the code for release. Do you see a difference in performance? We don't backpropagate the gradients through this, but the uv maps are used for tangent computation as you mentioned.

As far as I understand, the step that you mentioned reorders the vertices, right?
I am assuming your UV map is not a face?

[jugwangjin]

Thank you for replying.

As you said, the reordering vetices, can fix this.

However, when I'm testing on the code, there was no big differences.
Maybe it can show some robustness on your method.

ps) the extracted UV map is from the result of xatlas on the face model in the directory 'assets'