Skip to content

Fix default SDF value for interior voxels via flood-fill #36

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix default SDF value for interior voxels via flood-fill #36

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 22 additions & 1 deletion direct3d_s2/models/autoencoders/ss_vae.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,6 @@
# -*- coding: utf-8 -*-
import numpy as np
import scipy.ndimage as ndi
import torch
import torch.nn as nn
import torch.nn.functional as F
Expand Down Expand Up @@ -118,8 +120,27 @@ def sparse2mesh(self,
sparse_sdf_i, sparse_index_i = sparse_sdf[idx].squeeze(-1).cpu(), sparse_index[idx][..., 1:].detach().cpu()
sdf = torch.ones((voxel_resolution, voxel_resolution, voxel_resolution))
sdf[sparse_index_i[..., 0], sparse_index_i[..., 1], sparse_index_i[..., 2]] = sparse_sdf_i

# ---------------------------------------------------------------- #
# Fix default SDF value for _interior_ voxels via flood-fill. #
# The default for interior voxels should be -1 (not +1). #
# ---------------------------------------------------------------- #

active_mask = torch.zeros((voxel_resolution, voxel_resolution, voxel_resolution), dtype=torch.bool)
active_mask[sparse_index_i[..., 0], sparse_index_i[..., 1], sparse_index_i[..., 2]] = 1

sdf = sdf.numpy()
active_mask = active_mask.numpy()

# Flood‑fill from object boundary to find interior.
# Use active voxels to define the object boundary.
interior_mask = ndi.binary_fill_holes(active_mask)

# Set inactive voxels to -1 if they are interior
sdf[interior_mask & (~active_mask)] = -1.0

vertices, faces, _, _ = measure.marching_cubes(
sdf.numpy(),
sdf,
mc_threshold,
method="lewiner",
)
Expand Down