DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling

• URL: http://arxiv.org/abs/2402.08876v2
• Date: Sun, 2 Jun 2024 14:50:33 GMT
• Title: DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling
• Authors: Miguel Fainstein, Viviana Siless, Emmanuel Iarussi,
• Abstract summary: We learn a hyperbolic scaling of the unsigned distance field, which defines a new Eikonal problem with distinct boundary conditions. Our approach not only addresses the challenge of open surface representation but also demonstrates significant improvement in reconstruction quality and training performance.
• Score: 0.20287200280084108
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, there has been a growing interest in training Neural Networks to approximate Unsigned Distance Fields (UDFs) for representing open surfaces in the context of 3D reconstruction. However, UDFs are non-differentiable at the zero level set which leads to significant errors in distances and gradients, generally resulting in fragmented and discontinuous surfaces. In this paper, we propose to learn a hyperbolic scaling of the unsigned distance field, which defines a new Eikonal problem with distinct boundary conditions. This allows our formulation to integrate seamlessly with state-of-the-art continuously differentiable implicit neural representation networks, largely applied in the literature to represent signed distance fields. Our approach not only addresses the challenge of open surface representation but also demonstrates significant improvement in reconstruction quality and training performance. Moreover, the unlocked field's differentiability allows the accurate computation of essential topological properties such as normal directions and curvatures, pervasive in downstream tasks such as rendering. Through extensive experiments, we validate our approach across various data sets and against competitive baselines. The results demonstrate enhanced accuracy and up to an order of magnitude increase in speed compared to previous methods.

Related papers

• Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes [29.65562721329593]
  In this paper, we introduce a novel neural implicit representation based on unsigned distance fields (UDFs) In UODFs, the minimal unsigned distance from any spatial point to the shape surface is defined solely in one direction, contrasting with the multi-directional determination made by SDF and UDF. We verify the effectiveness of UODFs through a range of reconstruction examples, extending from watertight or non-watertight shapes to complex shapes.
  arXiv  Detail & Related papers  (2024-03-03T06:58:35Z)
• Neural Vector Fields: Implicit Representation by Explicit Learning [63.337294707047036]
  We propose a novel 3D representation method, Neural Vector Fields (NVF) It not only adopts the explicit learning process to manipulate meshes directly, but also the implicit representation of unsigned distance functions (UDFs) Our method first predicts displacement queries towards the surface and models shapes as text reconstructions.
  arXiv  Detail & Related papers  (2023-03-08T02:36:09Z)
• NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologies [87.06532943371575]
  We present a novel method, called NeuralUDF, for reconstructing surfaces with arbitrary topologies from 2D images via volume rendering. In this paper, we propose to represent surfaces as the Unsigned Distance Function (UDF) and develop a new volume rendering scheme to learn the neural UDF representation.
  arXiv  Detail & Related papers  (2022-11-25T15:21:45Z)
• 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)
• 3PSDF: Three-Pole Signed Distance Function for Learning Surfaces with Arbitrary Topologies [18.609959464825636]
  We present a novel learnable implicit representation called the three-pole signed distance function (3PSDF) It can represent non-watertight 3D shapes with arbitrary topologies while supporting easy field-to-mesh conversion. We propose a dedicated learning framework to effectively learn 3PSDF without worrying about the vanishing gradient due to the null labels.
  arXiv  Detail & Related papers  (2022-05-31T07:24:04Z)
• RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds [106.54285912111888]
  We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds. We show that RangeUDF clearly surpasses state-of-the-art approaches for surface reconstruction on four point cloud datasets.
  arXiv  Detail & Related papers  (2022-04-19T21:39:45Z)
• Neural Vector Fields for Implicit Surface Representation and Inference [73.25812045209001]
  Implicit fields have recently shown increasing success in representing and learning 3D shapes accurately. We develop a novel and yet a fundamental representation considering unit vectors in 3D space and call it Vector Field (VF) We show the advantages of VF representation, in learning open, closed, or multi-layered as well as piecewise planar surfaces.
  arXiv  Detail & Related papers  (2022-04-13T17:53:34Z)
• Attribute-Guided Adversarial Training for Robustness to Natural Perturbations [64.35805267250682]
  We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations.
  arXiv  Detail & Related papers  (2020-12-03T10:17:30Z)
• MeshSDF: Differentiable Iso-Surface Extraction [45.769838982991736]
  We introduce a differentiable way to produce explicit surface mesh representations from Deep Signed Distance Functions. Our key insight is that by reasoning on how implicit field perturbations impact local surface geometry, one can ultimately differentiate the 3D location of surface samples. We exploit this to define MeshSDF, an end-to-end differentiable mesh representation which can vary its topology.
  arXiv  Detail & Related papers  (2020-06-06T23:44:05Z)

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.