Learning a More Continuous Zero Level Set in Unsigned Distance Fields
through Level Set Projection
- URL: http://arxiv.org/abs/2308.11441v1
- Date: Tue, 22 Aug 2023 13:45:35 GMT
- Title: Learning a More Continuous Zero Level Set in Unsigned Distance Fields
through Level Set Projection
- Authors: Junsheng Zhou, Baorui Ma, Shujuan Li, Yu-Shen Liu, Zhizhong Han
- Abstract summary: 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.
- Score: 55.05706827963042
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Latest methods represent shapes with open surfaces using unsigned distance
functions (UDFs). They train neural networks to learn UDFs and reconstruct
surfaces with the gradients around the zero level set of the UDF. However, the
differential networks struggle from learning the zero level set where the UDF
is not differentiable, which leads to large errors on unsigned distances and
gradients around the zero level set, resulting in highly fragmented and
discontinuous surfaces. To resolve this problem, we propose to learn a more
continuous zero level set in UDFs with level set projections. Our insight is to
guide the learning of zero level set using the rest non-zero level sets via a
projection procedure. Our idea is inspired from the observations that the
non-zero level sets are much smoother and more continuous than the zero level
set. We pull the non-zero level sets onto the zero level set with gradient
constraints which align gradients over different level sets and correct
unsigned distance errors on the zero level set, leading to a smoother and more
continuous unsigned distance field. We conduct comprehensive experiments in
surface reconstruction for point clouds, real scans or depth maps, and further
explore the performance in unsupervised point cloud upsampling and unsupervised
point normal estimation with the learned UDF, which demonstrate our non-trivial
improvements over the state-of-the-art methods. Code is available at
https://github.com/junshengzhou/LevelSetUDF .
Related papers
- Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Clouds [34.774577477968805]
We propose a novel non-linear implicit filter to smooth the implicit field while preserving geometry details.
Our novelty lies in that we can filter the surface (zero level set) by the neighbor input points with gradients of the signed distance field.
By moving the input raw point clouds along the gradient, our proposed implicit filtering can be extended to non-zero level sets.
arXiv Detail & Related papers (2024-07-18T09:40:24Z) - Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction [26.35134181204119]
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.
arXiv Detail & Related papers (2024-06-01T07:52:26Z) - DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling [0.20287200280084108]
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.
arXiv Detail & Related papers (2024-02-14T00:42:19Z) - 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) - Unsupervised Inference of Signed Distance Functions from Single Sparse
Point Clouds without Learning Priors [54.966603013209685]
It is vital to infer signed distance functions (SDFs) from 3D point clouds.
We present a neural network to directly infer SDFs from single sparse point clouds.
arXiv Detail & Related papers (2023-03-25T15:56:50Z) - 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) - Semi-signed neural fitting for surface reconstruction from unoriented
point clouds [53.379712818791894]
We propose SSN-Fitting to reconstruct a better signed distance field.
SSN-Fitting consists of a semi-signed supervision and a loss-based region sampling strategy.
We conduct experiments to demonstrate that SSN-Fitting achieves state-of-the-art performance under different settings.
arXiv Detail & Related papers (2022-06-14T09:40:17Z) - Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors [52.25114448281418]
Current methods are able to reconstruct surfaces by learning Signed Distance Functions (SDFs) from single point clouds without ground truth signed distances or point normals.
We propose to reconstruct highly accurate surfaces from sparse point clouds with an on-surface prior.
Our method can learn SDFs from a single sparse point cloud without ground truth signed distances or point normals.
arXiv Detail & Related papers (2022-04-22T09:45:20Z)
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.