Comments (2)
Hi @raphaelsulzer unfortunately, the surface reconstruction benchmark only comes with dense point clouds for ground truth. See the ground_truth/
directory in the zip for this paper.
It would be pretty reasonable to simply mesh the very dense ground truth data and use that as a proxy for the real ground truth data. You can do that as follows with Point Cloud Utils
- Convert the dense ground truth files from
.xyz
to.ply
so they're easier to manage (See code below which does this) - Estimate normals for the dense point cloud. (See code below)
- Generate a mesh with e.g. Screened Poisson Surface Reconstruction
Estimating normals with point cloud utils:
import point_cloud_utils as pcu
import numpy as np
path_to_ply = "put your path here"
num_neighbors = 20 # Number of nearest neighbors to use for normal estimation. Tune this to control smoothness of normals
v, _, _, _ = pcu.read_ply(path_to_ply, dtype=np.float64)
n = pcu.estimate_normals(v, k=num_neighbors)
pcu.write_ply(path_to_ply[:-len(".ply")] + "-normals.ply, v, np.zeros([0, 3], dtype=np.int32), n.astype(v), np.zeros([0, 3], dtype=v.dtype))
Converting .xyz to .ply
import argparse
import numpy as np
import point_cloud_utils as pcu
def main():
argparser = argparse.ArgumentParser()
argparser.add_argument("xyz_path", type=str)
args = argparser.parse_args()
if not args.xyz_path.endswith(".xyz"):
raise ValueError("Input file must end in .xyz")
pts = []
with open(args.xyz_path) as f:
for line in f:
pts.append([float(c) for c in line.strip().split()])
pts = np.array(pts)
out_path = args.xyz_path[:-len("xyz")] + "ply"
print(out_path)
pcu.write_ply(out_path, pts, np.zeros([0, 3], dtype=np.int32),
np.zeros([0, 3], dtype=pts.dtype), np.zeros([0, 3], dtype=pts.dtype))
if __name__ == "__main__":
main()
from deep-geometric-prior.
Ok, I see. Thanks a lot for the explanation and the code! Great help!
from deep-geometric-prior.
Related Issues (10)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deep-geometric-prior.