You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Neural shape representation generally refers to representing 3D geometry using neural networks, e.g., computing a signed distance or occupancy value at a specific spatial position.
28
29
In this paper we present a neural-network architecture suitable for accurate encoding of 3D shapes in a single forward pass.
@@ -34,9 +35,38 @@ Furthermore, our network is trained to solve the well-established eikonal equati
34
35
We additionally propose a modification to the aforementioned loss function for the case that surface normals are not well defined, e.g., in the context of non-watertight surfaces and non-manifold geometry.
35
36
Overall, our method consistently outperforms other baselines on the surface reconstruction task across a wide variety of datasets, while being more computationally efficient and requiring fewer parameters.
36
37
37
-
## More coming soon!
38
+
## :rocket: Quickstart
38
39
39
-
# BibTeX
40
+
Its very easy to get started with our method simply run the following commands
0 commit comments