Diffusion-Driven Inter-Outer Surface Separation for Point Clouds with Open Boundaries

• URL: http://arxiv.org/abs/2602.00739v1
• Date: Sat, 31 Jan 2026 14:11:28 GMT
• Title: Diffusion-Driven Inter-Outer Surface Separation for Point Clouds with Open Boundaries
• Abstract summary: 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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a diffusion-based algorithm for separating the inter and outer layer surfaces from double-layered point clouds, particularly those exhibiting the "double surface artifact" caused by truncation in Truncated Signed Distance Function (TSDF) fusion during indoor or medical 3D reconstruction. This artifact arises from asymmetric truncation thresholds, leading to erroneous inter and outer shells in the fused volume, which our method addresses by extracting the true inter layer to mitigate challenges like overlapping surfaces and disordered normals. We focus on point clouds with \emph{open boundaries} (i.e., sampled surfaces with topological openings/holes through which particles may escape), rather than point clouds with \emph{missing surface regions} where no samples exist. Our approach enables robust processing of both watertight and open-boundary models, achieving extraction of the inter layer from 20,000 inter and 20,000 outer points in approximately 10 seconds. This solution is particularly effective for applications requiring accurate surface representations, such as indoor scene modeling and medical imaging, where double-layered point clouds are prevalent, and it accommodates both closed (watertight) and open-boundary surface geometries. Our goal is \emph{post-hoc} inter/outer shell separation as a lightweight module after TSDF fusion; we do not aim to replace full variational or learning-based reconstruction pipelines.

Related papers

• MidSurfNet: Learnable Face Pairing and Interference Implicit Fields for Generalized Mid-surface Abstraction [14.869951796629435]
  MidSurfNet is a learning-augmented framework that learns to predict face pair confidence from geometric and topological features.<n>We construct a large-scale mid-surface dataset containing over 1,500 manually annotated CAD models.
  arXiv  Detail & Related papers  (2026-06-01T08:36:02Z)
• UVTran: Accurate Hole-Filling Parameterization with Transformers [5.131212158757835]
  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.
  arXiv  Detail & Related papers  (2026-04-27T14:12:03Z)
• RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing [59.24689613992402]
  We introduce RefracGS, a framework that jointly reconstructs the refractive water surface and the scene beneath the interface.<n>RefracGS outperforms prior refractive methods in visual quality, while achieving 15x faster training and real-time rendering at 200 FPS.
  arXiv  Detail & Related papers  (2026-03-23T08:31:08Z)
• S2ML: Spatio-Spectral Mutual Learning for Depth Completion [56.26679539288063]
  Raw depth images captured by RGB-D cameras often suffer from incomplete depth values due to weak reflections, boundary shadows, and artifacts.<n>Existing methods address this problem through depth completion in the image domain, but they overlook the physical characteristics of raw depth images.<n>We propose a Spatio-Spectral Mutual Learning framework (S2ML) to harmonize the advantages of both spatial and frequency domains for depth completion.
  arXiv  Detail & Related papers  (2025-11-08T15:01:55Z)
• SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling [79.56581753856452]
  SparseFlex is a novel sparse-structured isosurface representation that enables differentiable mesh reconstruction at resolutions up to $10243$ directly from rendering losses.<n>By enabling high-resolution, differentiable mesh reconstruction and generation with rendering losses, SparseFlex significantly advances the state-of-the-art in 3D shape representation and modeling.
  arXiv  Detail & Related papers  (2025-03-27T17:46:42Z)
• Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes [59.17785932398617]
  High-quality view synthesis relies on volume rendering, splatting, or surface rendering.<n>We present a novel representation for real-time view synthesis where the number of sampling locations is small and bounded.<n>We achieve this by representing objects as semi-transparent multi-layer meshes rendered in a fixed order.
  arXiv  Detail & Related papers  (2024-09-04T07:18:26Z)
• DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting [39.510392485356284]
  We show that state-of-the-art techniques work by minimizing an approximation of a one-sided Chamfer distance. As a consequence, existing methods can produce inaccurate reconstructions with spurious surfaces. We propose DiffCD, a novel loss function corresponding to the symmetric Chamfer distance.
  arXiv  Detail & Related papers  (2024-07-24T07:36:33Z)
• Surface Reconstruction from Point Clouds via Grid-based Intersection Prediction [12.329450385760051]
  We propose a novel approach that directly predicts the intersection points between line segment of point pairs and implicit surfaces. Our approach demonstrates state-of-the-art performance on three datasets: ShapeNet, MGN, and ScanNet.
  arXiv  Detail & Related papers  (2024-03-21T02:31:17Z)
• 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)
• On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation [56.97699793236174]
  We study two kinds of robust cross-view consistency in this paper. We exploit the temporal coherence in both depth feature space and 3D voxel space for self-supervised monocular depth estimation. Experimental results on several outdoor benchmarks show that our method outperforms current state-of-the-art techniques.
  arXiv  Detail & Related papers  (2022-09-19T03:46:13Z)
• MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks [68.82901764109685]
  Recent work modelling 3D open surfaces train deep neural networks to approximate Unsigned Distance Fields (UDFs) We propose to directly mesh deep UDFs as open surfaces with an extension of marching cubes, by locally detecting surface crossings. Our method is order of magnitude faster than meshing a dense point cloud, and more accurate than inflating open surfaces.
  arXiv  Detail & Related papers  (2021-11-29T14:24:02Z)
• Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries [16.773787000535645]
  We propose a multi-hypothesis depth representation that explicitly models both foreground and background depths. Key to our method is the use of an asymmetric loss function that operates on a novel twin-surface representation. We validate our method on three different datasets.
  arXiv  Detail & Related papers  (2021-04-06T02:36:35Z)

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.