UVTran: Accurate Hole-Filling Parameterization with Transformers

• URL: http://arxiv.org/abs/2605.16306v1
• Date: Mon, 27 Apr 2026 14:12:03 GMT
• Title: UVTran: Accurate Hole-Filling Parameterization with Transformers
• Abstract summary: In industrial design, N-sided hole filling is typically formulated as the construction of a single trimmed B-spline surface.<n>We propose UVTran, a transformer-based framework that predicts an auxiliary projection surface better to capture the geometric characteristics of the hole boundary.
• Score: 5.131212158757835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In industrial design, N-sided hole filling is typically formulated as the construction of a single trimmed B-spline surface by minimizing a fairness energy subject to geometric boundary constraints. This formulation requires an accurate parameter-space representation of the trimming curve on the filling surface. Most existing methods project the hole boundary onto a nearby plane or polygon to establish correspondence; however, they often neglect boundary heterogeneity, which can yield biased mappings, degrade fairness, and even cause filling failures. We propose UVTran, a transformer-based framework that predicts an auxiliary projection surface better to capture the geometric characteristics of the hole boundary. Exploiting B-spline locality, we design a cross-attention mechanism that biases each surface control point toward the nearby hole boundary, preserving local geometric detail. We voxelize control-point coordinates and formulate the fitting problem as a classification task, which reduces the model's sensitivity to small numerical perturbations and noise. We adopt a progressive-resolution training strategy that injects controlled discretization errors at coarse resolutions to mimic distribution shifts, thereby mitigating overfitting and improving generalization at high resolution. On our benchmark, UVTran outperforms both industrial and academic baselines: the tolerance-satisfaction rate improves by $12\%$, and it consistently produces fair filled surfaces even under complex hole boundary conditions. These results suggest that UVTran yields more faithful correspondences and fairer trimmed surfaces across a wide range of N-sided holes.

Related papers

• Latent-Space No-Arbitrage Geometry of Generative Models for Implied Volatility Surfaces [1.8352395597748326]
  Generative models for implied volatility surfaces must produce outputs that satisfy static no-arbitrage constraints.<n>For a fixed generator, we assign each latent code a scalar margin determined by the no-arbitrage conditions of the generated surface.<n>We establish conditions under which strictly admissible codes remain admissible under small perturbations and the boundary of the admissible set is characterized by zero margin.
  arXiv  Detail & Related papers  (2026-08-31T20:27:40Z)
• Gaussian Sculpting: End-to-End Controllable Surface Reconstruction via Field Optimization [22.001328928240053]
  3D Gaussian Splatting has recently enabled real-time novel view synthesis with impressive quality.<n>It struggles to recover accurate surfaces under limited viewpoints and due to the inherent irregularity of Gaussian primitives.<n>We propose a fully differentiable end-to-end framework for high-quality surface reconstruction.
  arXiv  Detail & Related papers  (2026-08-11T07:42:24Z)
• Autoregressive B-Rep Shape Generation with Parametric Surfaces [83.03418080213359]
  ParaCAD is an autoregressive framework for point-cloud-conditioned B-Rep generation.<n>Our model first generates parametric surfaces with constrained UV domains, and then constructs a valid B-Rep by globally intersecting these surfaces.<n>Extensive experiments demonstrate that ParaCAD produces accurate B-Reps with faithful point-cloud alignment.
  arXiv  Detail & Related papers  (2026-07-19T06:14:50Z)
• A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning [52.452902154360565]
  We introduce Mean Curvature Boundary Points (MCBP), a novel geometric framework grounded in Geometric Machine Learning.<n>MCBP explicitly models the intrinsic curvature of the data manifold and computes pointwise mean curvature without requiring principled manifold parametrization.<n>Experiments on synthetic and real-world datasets demonstrate that MCBP consistently improves clustering performance.
  arXiv  Detail & Related papers  (2026-05-05T20:19:09Z)
• Simultaneous CNN Approximation on Manifolds with Applications to Boundary Value Problems [2.815765641180636]
  This paper develops convolutional neural network (CNN) methods for simultaneous approximation and elliptic boundary value problems.<n>We establish simultaneous Sobolev approximation results for single- and multichannel CNNs.<n>We propose a physics-informed CNN framework specially designed for boundary value problems.
  arXiv  Detail & Related papers  (2026-05-05T15:35:24Z)
• From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians [36.88207476975372]
  3D Gaussian Splatting has revolutionized fast novel view synthesis, yet its opacity-based formulation makes surface extraction difficult.<n>We show how it can be used to extract highly accurate watertight meshes of complex scenes.<n>Our method sets a new state-of-the-art on DTU and Tanks and Temples, producing complete, watertight meshes at a fraction of the size of concurrent work-recovering thin structures.
  arXiv  Detail & Related papers  (2026-04-08T17:52:39Z)
• Diffusion-Driven Inter-Outer Surface Separation for Point Clouds with Open Boundaries [0.0]
  We propose a diffusion-based algorithm for separating the inter and outer layer surfaces from double-layered point clouds.<n>This solution is particularly effective for applications requiring accurate surface representations, such as indoor scene modeling and medical imaging.
  arXiv  Detail & Related papers  (2026-01-31T14:11:28Z)
• GLOBE: Accurate and Generalizable PDE Surrogates using Domain-Inspired Architectures and Equivariances [0.0]
  GLOBE represents solutions as superpositions of learnable Green's-function-like kernels evaluated from boundary faces to targets.<n>On AirFRANS, GLOBE achieves substantial accuracy improvements.<n>Results show that rigorous physics- and domain-inspired inductive biases can achieve large gains in accuracy, generalizability, and practicality.
  arXiv  Detail & Related papers  (2025-11-19T20:23:51Z)
• ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction [50.07671826433922]
  It is non-trivial to simultaneously recover meticulous geometry and preserve smoothness across regions with differing characteristics.<n>We propose ND-SDF, which learns a Normal Deflection field to represent the angular deviation between the scene normal and the prior normal.<n>Our method not only obtains smooth weakly textured regions such as walls and floors but also preserves the geometric details of complex structures.
  arXiv  Detail & Related papers  (2024-08-22T17:59:01Z)
• Improving Gaussian Splatting with Localized Points Management [52.009874685460694]
  Localized Point Management (LPM) is capable of identifying those error-contributing zones in greatest need for both point addition and geometry calibration.<n>LPM applies point densification in the identified zones and then reset the opacity of the points in front of these regions, creating a new opportunity to correct poorly conditioned points.<n> Notably, LPM improves both static 3DGS and dynamic SpaceTimeGS to achieve state-of-the-art rendering quality while retaining real-time speeds.
  arXiv  Detail & Related papers  (2024-06-06T16:55:07Z)
• Flatten Anything: Unsupervised Neural Surface Parameterization [76.4422287292541]
  We introduce the Flatten Anything Model (FAM), an unsupervised neural architecture to achieve global free-boundary surface parameterization. Compared with previous methods, our FAM directly operates on discrete surface points without utilizing connectivity information. Our FAM is fully-automated without the need for pre-cutting and can deal with highly-complex topologies.
  arXiv  Detail & Related papers  (2024-05-23T14:39:52Z)
• Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis [70.40950409274312]
  We modify density fields to encourage them to converge towards surfaces, without compromising their ability to reconstruct thin structures. We also develop a fusion-based meshing strategy followed by mesh simplification and appearance model fitting. The compact meshes produced by our model can be rendered in real-time on mobile devices.
  arXiv  Detail & Related papers  (2024-02-19T18:59:41Z)

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.