Surface Reconstruction Based on Neural Networks

Surface reconstruction is an important trend in 3D scanning. The problem is to recreate surfaces from a given point cloud within the shortest possible time and with a given quality criteria. There is a set of different approaches for solving this problem, which includes Self-Organized Maps, Bayesian reconstruction and Poisson reconstruction.

The aim of the research is to find the most suitable method based on Machine Learning unsupervised learning techniques for reconstruction of interior and exterior 3D scans of original objects. The self-organizing map type of the artificial neural network was chosen due to its ability to produce good results without restrictions on point cloud size and points’ order. It can generate meshes from a small number of point samples in an unorganized point cloud.

The purpose of this paper is to analyze and compare results obtained with the usage of two self-organizing map types – Surface Growing Neural Gas (sGNG) and Growing Cell Structures (GCS) reconstruction – for reconstruction of a 3D mesh from point cloud. In addition, the sGNG extension to multithreading is presented and compared to the original approach.

Read the full article here:

AMC Bridge Webinars

Industry experts share their knowledge, advice, and insights

AMC Bridge news

  • Partnerships

    Oct 14, 2026

    AMC Bridge for Onshape: Extend, Integrate, and Scale Onshape Across Your Enterprise

    Onshape brings cloud-native CAD and PDM to your engineering teams. AMC Bridge connects it to the rest of your business. Since 2013, we have helped manufacturers extend Onshape beyond out-of-the-box functionality by integrating it with PLM, ERP, and MES systems, migrating legacy data, and supporting adoption across complex engineering environments.
  • Case study

    Oct 02, 2026

    AMC Bridge Enables AI-Ready Digital Thread Across the Engineering Lifecycle for Leading Research and Engineering Organization

    AMC Bridge, a software technology company serving engineering, manufacturing, and construction organizations, announced the successful delivery of a digital thread initiative for a leading research and engineering organization supporting complex, mission-critical programs. The engagement established a connected digital engineering environment that links systems engineering, design, manufacturing, and testing data, creating a scalable foundation for improved decision-making and future AI adoption.
  • Technology demonstration

    Sep 30, 2026

    AMC Bridge Introduces System Engineering–Driven Digital Thread Built on Aras Innovator

    Engineering organizations developing complex products increasingly struggle to maintain visibility and traceability across requirements, system architecture, manufacturing, and validation activities. As programs grow in complexity, disconnected engineering tools and siloed data often create gaps in communication, slow decision-making, and limit the ability to understand the true status of products and programs.
Discover
-