Challenges in 3D Data Synthesis for Training Neural Networks on Topological Features

• URL: http://arxiv.org/abs/2511.04972v1
• Date: Fri, 07 Nov 2025 04:15:32 GMT
• Title: Challenges in 3D Data Synthesis for Training Neural Networks on Topological Features
• Authors: Dylan Peek, Matthew P. Skerritt, Siddharth Pritam, Stephan Chalup,
• Abstract summary: Topological Data Analysis involves techniques of analyzing the underlying structure and connectivity of data.<n>Traditional methods like persistent homology can be computationally demanding, motivating the development of neural network-based estimators.<n>Key barrier to advancing these methods is the lack of labeled 3D data with class distributions and diversity tailored specifically for supervised learning.<n>This paper uses a synthetic 3D dataset to train a genus estimator network, created using a 3D convolutional transformer architecture.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Topological Data Analysis (TDA) involves techniques of analyzing the underlying structure and connectivity of data. However, traditional methods like persistent homology can be computationally demanding, motivating the development of neural network-based estimators capable of reducing computational overhead and inference time. A key barrier to advancing these methods is the lack of labeled 3D data with class distributions and diversity tailored specifically for supervised learning in TDA tasks. To address this, we introduce a novel approach for systematically generating labeled 3D datasets using the Repulsive Surface algorithm, allowing control over topological invariants, such as hole count. The resulting dataset offers varied geometry with topological labeling, making it suitable for training and benchmarking neural network estimators. This paper uses a synthetic 3D dataset to train a genus estimator network, created using a 3D convolutional transformer architecture. An observed decrease in accuracy as deformations increase highlights the role of not just topological complexity, but also geometric complexity, when training generalized estimators. This dataset fills a gap in labeled 3D datasets and generation for training and evaluating models and techniques for TDA.

Related papers

• Tail-Aware Post-Training Quantization for 3D Geometry Models [58.79500829118265]
  Post-Training Quantization (PTQ) enables efficient inference without retraining.<n>PTQ fails to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead.<n>We propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline for 3D geometric learning.
  arXiv  Detail & Related papers  (2026-02-02T07:21:15Z)
• Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition [63.55828203989405]
  We introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds.<n>Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures.<n>We propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training.
  arXiv  Detail & Related papers  (2025-06-26T11:53:59Z)
• MeshConv3D: Efficient convolution and pooling operators for triangular 3D meshes [0.0]
  MeshConv3D is a 3D mesh-dedicated methodology integrating specialized convolution and face collapse-based pooling operators.<n>The experimental results obtained on three distinct benchmark datasets show that the proposed approach makes it possible to achieve equivalent or superior classification results.
  arXiv  Detail & Related papers  (2025-01-07T14:41:26Z)
• Differentiable Topology Estimating from Curvatures for 3D Shapes [5.122262236258208]
  This paper introduces a novel, differentiable algorithm tailored to accurately estimate the global topology of 3D shapes.<n>It ensures high accuracy, efficiency, and instant computation with GPU compatibility.<n> Experimental results demonstrate the method's superior performance across various datasets.
  arXiv  Detail & Related papers  (2024-11-28T17:14:35Z)
• Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration [2.814748676983944]
  We propose a graph neural network model embedded with a local Spherical Euclidean 3D equivariance property through SE(3) message passing based propagation. Our model is composed mainly of a descriptor module, equivariant graph layers, match similarity, and the final regression layers. Experiments conducted on the 3DMatch and KITTI datasets exhibit the compelling and robust performance of our model compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-10-08T06:48:01Z)
• Synthetic Data Generation and Deep Learning for the Topological Analysis of 3D Data [0.0]
  This research uses deep learning to estimate the topology of sparse, unordered point cloud scenes in 3D. The experimental results of this pilot study support the hypothesis that, with the aid of sophisticated synthetic data generation, neural networks can perform segmentation-based topological data analysis.
  arXiv  Detail & Related papers  (2023-09-29T04:37:35Z)
• Geometry-Contrastive Transformer for Generalized 3D Pose Transfer [95.56457218144983]
  The intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism. We propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies. We present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task.
  arXiv  Detail & Related papers  (2021-12-14T13:14:24Z)
• Scene Synthesis via Uncertainty-Driven Attribute Synchronization [52.31834816911887]
  This paper introduces a novel neural scene synthesis approach that can capture diverse feature patterns of 3D scenes. Our method combines the strength of both neural network-based and conventional scene synthesis approaches.
  arXiv  Detail & Related papers  (2021-08-30T19:45:07Z)
• TSGCNet: Discriminative Geometric Feature Learning with Two-Stream GraphConvolutional Network for 3D Dental Model Segmentation [141.2690520327948]
  We propose a two-stream graph convolutional network (TSGCNet) to learn multi-view information from different geometric attributes. We evaluate our proposed TSGCNet on a real-patient dataset of dental models acquired by 3D intraoral scanners.
  arXiv  Detail & Related papers  (2020-12-26T08:02:56Z)
• DEF: Deep Estimation of Sharp Geometric Features in 3D Shapes [43.853000396885626]
  We propose a learning-based framework for predicting sharp geometric features in sampled 3D shapes. By fusing the result of individual patches, we can process large 3D models, which are impossible to process for existing data-driven methods.
  arXiv  Detail & Related papers  (2020-11-30T18:21:00Z)
• Learning Local Neighboring Structure for Robust 3D Shape Representation [143.15904669246697]
  Representation learning for 3D meshes is important in many computer vision and graphics applications. We propose a local structure-aware anisotropic convolutional operation (LSA-Conv) Our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-21T13:40:03Z)

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.