Neural Surface Detection for Unsigned Distance Fields

• URL: http://arxiv.org/abs/2407.18381v2
• Date: Sun, 27 Oct 2024 12:58:06 GMT
• Title: Neural Surface Detection for Unsigned Distance Fields
• Authors: Federico Stella, Nicolas Talabot, Hieu Le, Pascal Fua,
• Abstract summary: We introduce a deep-learning approach to taking a UDF and turning it locally into an SDF, so that it can be effectively triangulated using existing algorithms. We show that it achieves better accuracy in surface detection than existing methods. We also demonstrate the flexibily of the method by using it in conjunction with DualMeshUDF, a state of the art dual meshing method that can operate on UDFs.
• Score: 51.77214039267625
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Extracting surfaces from Signed Distance Fields (SDFs) can be accomplished using traditional algorithms, such as Marching Cubes. However, since they rely on sign flips across the surface, these algorithms cannot be used directly on Unsigned Distance Fields (UDFs). In this work, we introduce a deep-learning approach to taking a UDF and turning it locally into an SDF, so that it can be effectively triangulated using existing algorithms. We show that it achieves better accuracy in surface detection than existing methods. Furthermore it generalizes well to unseen shapes and datasets, while being parallelizable. We also demonstrate the flexibily of the method by using it in conjunction with DualMeshUDF, a state of the art dual meshing method that can operate on UDFs, improving its results and removing the need to tune its parameters.

Related papers

• Voronoi-Assisted Diffusion for Computing Unsigned Distance Fields from Unoriented Points [59.493891955043914]
  Voronoi-Assisted Diffusion (VAD) is a lightweight, network-free method for computing Unsigned Distance Fields (UDFs)<n>VAD robustly handles watertight and open surfaces, as well as complex non-manifold and non-orientable geometries.
  arXiv  Detail & Related papers  (2025-10-14T13:49:53Z)
• High Resolution UDF Meshing via Iterative Networks [35.20698867678239]
  Unsigned Distance Fields (UDFs) are a natural implicit representation for open surfaces but, unlike Signed Distance Fields (SDFs), are challenging to triangulate into explicit meshes.<n>This is especially true at high resolutions where neural UDFs exhibit higher noise levels, which makes it hard to capture fine details.<n>We show that this can be remedied by performing several passes and by reasoning on previously extracted surface elements to incorporate neighborhood information.<n>Our key contribution is an iterative neural network that does this and progressively improves surface recovery within each voxel by spatially propagating information from increasingly distant neighbors.
  arXiv  Detail & Related papers  (2025-09-21T19:39:54Z)
• MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction [21.026007872505712]
  Unsigned distance fields are widely used in 3D deep learning.<n> extracting meshes from UDFs remains challenging, as the learned fields rarely attain exact zero distances.<n>A common workaround is to reconstruct signed distance fields (SDFs) locally from UDFs to enable surface extraction via Marching Cubes.<n>We propose MIND, a novel algorithm for generating material interfaces directly from UDFs.
  arXiv  Detail & Related papers  (2025-06-03T14:37:11Z)
• Gradient Distance Function [52.615859148238464]
  We show that Gradient Distance Functions (GDFs) can be differentiable at the surface while still being able to represent open surfaces. This is done by associating to each 3D point a 3D vector whose norm is taken to be the unsigned distance to the surface. We demonstrate the effectiveness of GDFs on ShapeNet Car, Multi-Garment, and 3D-Scene datasets.
  arXiv  Detail & Related papers  (2024-10-29T18:04:01Z)
• Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Clouds [69.69726932986923]
  We propose the scaled-squared distance function (S$2$DF), a novel implicit surface representation for modeling arbitrary surface types. S$2$DF does not distinguish between inside and outside regions while effectively addressing the non-differentiability issue of UDF at the zero level set. We demonstrate that S$2$DF satisfies a second-order partial differential equation of Monge-Ampere-type.
  arXiv  Detail & Related papers  (2024-10-24T06:56:34Z)
• Statistical Edge Detection And UDF Learning For Shape Representation [1.9799527196428242]
  We propose a method for learning UDFs that improves the fidelity of the obtained Neural UDF to the original 3D surface. We show that sampling more training points around surface edges allows better local accuracy of the trained Neural UDF. Our method is shown to detect surface edges more accurately than a commonly used local geometric descriptor.
  arXiv  Detail & Related papers  (2024-05-06T11:40:57Z)
• Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Covering [28.268387694075415]
  We propose a new method for extracting the zero level-set from unsigned distance fields (UDFs) DoubleCoverUDF takes a learned UDF and a user-specified parameter $r$ as input. We show that the computed iso-surface is the boundary of the $r$-offset volume of the target zero level-set $S$.
  arXiv  Detail & Related papers  (2023-10-05T10:17:30Z)
• CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization [54.69408516025872]
  CAP-UDF is a novel method to learn consistency-aware UDF from raw point clouds. We train a neural network to gradually infer the relationship between queries and the approximated surface. We also introduce a polygonization algorithm to extract surfaces using the gradients of the learned UDF.
  arXiv  Detail & Related papers  (2022-10-06T08:51:08Z)
• iSDF: Real-Time Neural Signed Distance Fields for Robot Perception [64.80458128766254]
  iSDF is a continuous learning system for real-time signed distance field reconstruction. It produces more accurate reconstructions and better approximations of collision costs and gradients.
  arXiv  Detail & Related papers  (2022-04-05T15:48:39Z)
• MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks [68.82901764109685]
  Recent work modelling 3D open surfaces train deep neural networks to approximate Unsigned Distance Fields (UDFs) We propose to directly mesh deep UDFs as open surfaces with an extension of marching cubes, by locally detecting surface crossings. Our method is order of magnitude faster than meshing a dense point cloud, and more accurate than inflating open surfaces.
  arXiv  Detail & Related papers  (2021-11-29T14:24:02Z)
• DUDE: Deep Unsigned Distance Embeddings for Hi-Fidelity Representation of Complex 3D Surfaces [8.104199886760275]
  DUDE is a disentangled shape representation that utilizes an unsigned distance field (uDF) to represent proximity to a surface, and a normal vector field (nVF) to represent surface orientation. We show that a combination of these two (uDF+nVF) can be used to learn high fidelity representations for arbitrary open/closed shapes.
  arXiv  Detail & Related papers  (2020-11-04T22:49:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.