Joint Orientation and Weight Optimization for Robust Watertight Surface Reconstruction via Dirichlet-Regularized Winding Fields

• URL: http://arxiv.org/abs/2602.13801v1
• Date: Sat, 14 Feb 2026 14:27:07 GMT
• Title: Joint Orientation and Weight Optimization for Robust Watertight Surface Reconstruction via Dirichlet-Regularized Winding Fields
• Authors: Jiaze Li, Daisheng Jin, Fei Hou, Junhui Hou, Zheng Liu, Shiqing Xin, Wenping Wang, Ying He,
• Abstract summary: Dirichlet Winding Reconstruction (DiWR) is a robust method for reconstructing watertight surfaces from unoriented point clouds.<n>Our method uses the generalized winding number (GWN) field as the target implicit representation.
• Score: 77.36628820738271
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose Dirichlet Winding Reconstruction (DiWR), a robust method for reconstructing watertight surfaces from unoriented point clouds with non-uniform sampling, noise, and outliers. Our method uses the generalized winding number (GWN) field as the target implicit representation and jointly optimizes point orientations, per-point area weights, and confidence coefficients in a single pipeline. The optimization minimizes the Dirichlet energy of the induced winding field together with additional GWN-based constraints, allowing DiWR to compensate for non-uniform sampling, reduce the impact of noise, and downweight outliers during reconstruction, with no reliance on separate preprocessing. We evaluate DiWR on point clouds from 3D Gaussian Splatting, a computer-vision pipeline, and corrupted graphics benchmarks. Experiments show that DiWR produces plausible watertight surfaces on these challenging inputs and outperforms both traditional multi-stage pipelines and recent joint orientation-reconstruction methods.

Related papers

• Structure-Informed Estimation for Pilot-Limited MIMO Channels via Tensor Decomposition [51.56484100374058]
  This paper formulates pilot-limited channel estimation as low-rank tensor completion from sparse observations.<n>Experiments on synthetic channels demonstrate 10-20,dB normalized mean-square error (NMSE) improvement over least-squares (LS)<n> evaluations on DeepMIMO ray-tracing channels show 24-44% additional NMSE reduction over pure tensor-based methods.
  arXiv  Detail & Related papers  (2026-02-03T23:38:05Z)
• Tubular Riemannian Laplace Approximations for Bayesian Neural Networks [0.0]
  Laplace approximations are among the simplest and most practical methods for approximate Bayesian inference in neural networks.<n>Recent work has proposed geometric Gaussian approximations to adapt to this structure.<n>We introduce the Tubular Riemannian Laplace (TRL) approximation.
  arXiv  Detail & Related papers  (2025-12-30T17:50:55Z)
• Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance [52.705112811734566]
  A novel diffusion-based framework is introduced for solving inverse problems using a piecewise guidance scheme.<n>The proposed method is problem-agnostic and readily adaptable to a variety of inverse problems.<n>The framework achieves a reduction in inference time of (25%) for inpainting with both random and center masks, and (23%) and (24%) for (4times) and (8times) super-resolution tasks.
  arXiv  Detail & Related papers  (2025-07-22T19:35:14Z)
• 3-Dimensional CryoEM Pose Estimation and Shift Correction Pipeline [2.009945677846956]
  Accurate pose estimation and shift correction are key challenges in cryo-EM due to the very low SNR, which directly impacts the fidelity of 3D reconstructions.<n>We present an approach for pose estimation in cryo-EM that leverages multi-dimensional scaling (MDS) techniques in a robust manner to estimate the 3D rotation matrix of each particle from pairs of dihedral angles.
  arXiv  Detail & Related papers  (2025-07-20T11:46:17Z)
• 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)
• High-quality Surface Reconstruction using Gaussian Surfels [18.51978059665113]
  We propose a novel point-based representation, Gaussian surfels, to combine the advantages of the flexible optimization procedure in 3D Gaussian points. This is achieved by setting the z-scale of 3D Gaussian points to 0, effectively flattening the original 3D ellipsoid into a 2D ellipse. By treating the local z-axis as the normal direction, it greatly improves optimization stability and surface alignment.
  arXiv  Detail & Related papers  (2024-04-27T04:13:39Z)
• Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance [52.093434664236014]
  Recent diffusion models provide a promising zero-shot solution to noisy linear inverse problems without retraining for specific inverse problems. Inspired by this finding, we propose to improve recent methods by using more principled covariance determined by maximum likelihood estimation.
  arXiv  Detail & Related papers  (2024-02-03T13:35:39Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• An automated parameter domain decomposition approach for gravitational wave surrogates using hp-greedy refinement [0.3867363075280544]
  hp-greedy is a refinement approach for building gravitational wave surrogates. We present a more realistic use case of gravitational waves emitted by the collision of two spinning, non-precessing black holes.
  arXiv  Detail & Related papers  (2022-12-16T16:12:51Z)
• Latent reweighting, an almost free improvement for GANs [12.605607949417033]
  A line of works aims at improving the sampling quality from pre-trained generators at the expense of increased computational cost. We introduce an additional network to predict latent importance weights and two associated sampling methods to avoid the poorest samples.
  arXiv  Detail & Related papers  (2021-10-19T08:33:57Z)

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.