Point Cloud to Mesh Reconstruction: Methods, Trade-offs, and Implementation Guide

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Iguenfer, Fatima Zahra, Hsain, Achraf, Amissa, Hiba, Chtouki, Yousra
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908745221537792
author Iguenfer, Fatima Zahra
Hsain, Achraf
Amissa, Hiba
Chtouki, Yousra
author_facet Iguenfer, Fatima Zahra
Hsain, Achraf
Amissa, Hiba
Chtouki, Yousra
contents Reconstructing meshes from point clouds is a fundamental task in computer vision with applications spanning robotics, autonomous systems, and medical imaging. Selecting an appropriate learning-based method requires understanding trade-offs between computational efficiency, geometric accuracy, and output constraints. This paper categorizes over fifteen methods into five paradigms -- PointNet family, autoencoder architectures, deformation-based methods, point-move techniques, and primitive-based approaches -- and provides practical guidance for method selection. We contribute: (1) a decision framework mapping input/output requirements to suitable paradigms, (2) a failure mode analysis to assist practitioners in debugging implementations, (3) standardized comparisons on ShapeNet benchmarks, and (4) a curated list of maintained codebases with implementation resources. By synthesizing both theoretical foundations and practical considerations, this work serves as an entry point for practitioners and researchers new to learning-based 3D mesh reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10977
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Point Cloud to Mesh Reconstruction: Methods, Trade-offs, and Implementation Guide
Iguenfer, Fatima Zahra
Hsain, Achraf
Amissa, Hiba
Chtouki, Yousra
Computer Vision and Pattern Recognition
Graphics
Reconstructing meshes from point clouds is a fundamental task in computer vision with applications spanning robotics, autonomous systems, and medical imaging. Selecting an appropriate learning-based method requires understanding trade-offs between computational efficiency, geometric accuracy, and output constraints. This paper categorizes over fifteen methods into five paradigms -- PointNet family, autoencoder architectures, deformation-based methods, point-move techniques, and primitive-based approaches -- and provides practical guidance for method selection. We contribute: (1) a decision framework mapping input/output requirements to suitable paradigms, (2) a failure mode analysis to assist practitioners in debugging implementations, (3) standardized comparisons on ShapeNet benchmarks, and (4) a curated list of maintained codebases with implementation resources. By synthesizing both theoretical foundations and practical considerations, this work serves as an entry point for practitioners and researchers new to learning-based 3D mesh reconstruction.
title Point Cloud to Mesh Reconstruction: Methods, Trade-offs, and Implementation Guide
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2412.10977