Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction

• URL: http://arxiv.org/abs/2406.00346v1
• Date: Sat, 1 Jun 2024 07:52:26 GMT
• Title: Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction
• Authors: Cheng Xu, Fei Hou, Wencheng Wang, Hong Qin, Zhebin Zhang, Ying He,
• Abstract summary: We propose Details Enhanced UDF (DEUDF) learning that integrates normal alignment and the SIREN network for capturing fine details. Our computational results demonstrate that DEUDF outperforms existing UDF learning methods in both accuracy and the quality of reconstructed surfaces.
• Score: 26.35134181204119
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Signed Distance Fields (SDF) are well-established for modeling watertight surfaces, Unsigned Distance Fields (UDF) broaden the scope to include open surfaces and models with complex inner structures. Despite their flexibility, UDFs encounter significant challenges in high-fidelity 3D reconstruction, such as non-differentiability at the zero level set, difficulty in achieving the exact zero value, numerous local minima, vanishing gradients, and oscillating gradient directions near the zero level set. To address these challenges, we propose Details Enhanced UDF (DEUDF) learning that integrates normal alignment and the SIREN network for capturing fine geometric details, adaptively weighted Eikonal constraints to address vanishing gradients near the target surface, unconditioned MLP-based UDF representation to relax non-negativity constraints, and a UDF-tailored method for extracting iso-surface with non-constant iso-values. These strategies collectively stabilize the learning process from unoriented point clouds and enhance the accuracy of UDFs. Our computational results demonstrate that DEUDF outperforms existing UDF learning methods in both accuracy and the quality of reconstructed surfaces. We will make the source code publicly available.

Related papers

• DCUDF2: Improving Efficiency and Accuracy in Extracting Zero Level Sets from Unsigned Distance Fields [11.397415082340482]
  Unsigned distance fields (UDFs) allow for the representation of models with complex topologies, but accurate zero level sets from these fields poses significant challenges. We introduceDF2, an enhancement over the current state-of-the-art method--for extracting zero level sets from UDFs. Our approach utilizes an accuracy-aware loss function, enhanced with self-adaptive weights, to improve geometric quality significantly.
  arXiv  Detail & Related papers  (2024-08-30T13:31:15Z)
• RaNeuS: Ray-adaptive Neural Surface Reconstruction [87.20343320266215]
  We leverage a differentiable radiance field eg NeRF to reconstruct detailed 3D surfaces in addition to producing novel view renderings. Considering that different methods formulate and optimize the projection from SDF to radiance field with a globally constant Eikonal regularization, we improve with a ray-wise weighting factor. Our proposed textitRaNeuS are extensively evaluated on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2024-06-14T07:54:25Z)
• 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)
• Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection [55.05706827963042]
  Latest methods represent shapes with open surfaces using unsigned distance functions (UDFs) We train neural networks to learn UDFs and reconstruct surfaces with the gradients around the zero level set of the UDF. We propose to learn a more continuous zero level set in UDFs with level set projections.
  arXiv  Detail & Related papers  (2023-08-22T13:45:35Z)
• Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment [50.892158511845466]
  We show that gradient consistency in the field, indicated by the parallelism of level sets, is the key factor affecting the inference accuracy. We propose a level set alignment loss to evaluate the parallelism of level sets, which can be minimized to achieve better gradient consistency.
  arXiv  Detail & Related papers  (2023-05-19T11:28:05Z)
• NeUDF: Leaning Neural Unsigned Distance Fields with Volume Rendering [25.078149064632218]
  NeUDF can reconstruct surfaces with arbitrary topologies solely from multi-view supervision. We extensively evaluate our method over a number of challenging datasets, including DTU, MGN, and Deep Fashion 3D.
  arXiv  Detail & Related papers  (2023-04-20T04:14:42Z)
• GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation [73.77505964222632]
  We present a learning-based method, namely GeoUDF, to tackle the problem of reconstructing a discrete surface from a sparse point cloud. To be specific, we propose a geometry-guided learning method for UDF and its gradient estimation. To extract triangle meshes from the predicted UDF, we propose a customized edge-based marching cube module.
  arXiv  Detail & Related papers  (2022-11-30T06:02:01Z)
• 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)

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.