Learnable Point Cloud Sampling Considering Seed Point for Neural Surface Reconstruction

Reconstruction of surfaces from point clouds is essential in numerous practical applications. An approach in which neural fields are trained as surface representations from point clouds has garnered significant interest in recent years. However, these techniques present scalability issues to large s...

Full description

Saved in:
Bibliographic Details
Main Authors: Kohei Matsuzaki, Keisuke Nonaka
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10804151/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850254936808357888
author Kohei Matsuzaki
Keisuke Nonaka
author_facet Kohei Matsuzaki
Keisuke Nonaka
author_sort Kohei Matsuzaki
collection DOAJ
description Reconstruction of surfaces from point clouds is essential in numerous practical applications. An approach in which neural fields are trained as surface representations from point clouds has garnered significant interest in recent years. However, these techniques present scalability issues to large scenes since they are limited in the size of point clouds that can be processed. This work proposes a learnable point cloud sampling designed to address the scalability issues. We introduce a sampling network that considers a seed point acting as the origin to sample points from a part of the scene. The seed point is one of the input points that is selected in a spatially uniform manner. This prompts a surface reconstruction network to learn the detailed geometry on partial regions of the scene. We also propose a training pipeline based on point cloud splitting and merging to avoid an increase in the memory footprint. We jointly train the sampling network and surface reconstruction network using a task loss to optimize the sampling network for the surface reconstruction task. Experimental results on scene-level datasets captured from real-world environments demonstrate that our method performs better than state-of-the-art methods in surface reconstruction.
format Article
id doaj-art-1633107d330b46aabc2fb342a6dedfce
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-1633107d330b46aabc2fb342a6dedfce2025-08-20T01:57:00ZengIEEEIEEE Access2169-35362024-01-011219094519095810.1109/ACCESS.2024.351862010804151Learnable Point Cloud Sampling Considering Seed Point for Neural Surface ReconstructionKohei Matsuzaki0https://orcid.org/0000-0001-9386-2192Keisuke Nonaka1https://orcid.org/0000-0002-9701-28623D Space Transmission Laboratory, KDDI Research, Inc., Fujimino, Saitama, Japan3D Space Transmission Laboratory, KDDI Research, Inc., Fujimino, Saitama, JapanReconstruction of surfaces from point clouds is essential in numerous practical applications. An approach in which neural fields are trained as surface representations from point clouds has garnered significant interest in recent years. However, these techniques present scalability issues to large scenes since they are limited in the size of point clouds that can be processed. This work proposes a learnable point cloud sampling designed to address the scalability issues. We introduce a sampling network that considers a seed point acting as the origin to sample points from a part of the scene. The seed point is one of the input points that is selected in a spatially uniform manner. This prompts a surface reconstruction network to learn the detailed geometry on partial regions of the scene. We also propose a training pipeline based on point cloud splitting and merging to avoid an increase in the memory footprint. We jointly train the sampling network and surface reconstruction network using a task loss to optimize the sampling network for the surface reconstruction task. Experimental results on scene-level datasets captured from real-world environments demonstrate that our method performs better than state-of-the-art methods in surface reconstruction.https://ieeexplore.ieee.org/document/10804151/Point cloud samplingsurface reconstructionneural fieldsseed pointlocal geometry
spellingShingle Kohei Matsuzaki
Keisuke Nonaka
Learnable Point Cloud Sampling Considering Seed Point for Neural Surface Reconstruction
IEEE Access
Point cloud sampling
surface reconstruction
neural fields
seed point
local geometry
title Learnable Point Cloud Sampling Considering Seed Point for Neural Surface Reconstruction
title_full Learnable Point Cloud Sampling Considering Seed Point for Neural Surface Reconstruction
title_fullStr Learnable Point Cloud Sampling Considering Seed Point for Neural Surface Reconstruction
title_full_unstemmed Learnable Point Cloud Sampling Considering Seed Point for Neural Surface Reconstruction
title_short Learnable Point Cloud Sampling Considering Seed Point for Neural Surface Reconstruction
title_sort learnable point cloud sampling considering seed point for neural surface reconstruction
topic Point cloud sampling
surface reconstruction
neural fields
seed point
local geometry
url https://ieeexplore.ieee.org/document/10804151/
work_keys_str_mv AT koheimatsuzaki learnablepointcloudsamplingconsideringseedpointforneuralsurfacereconstruction
AT keisukenonaka learnablepointcloudsamplingconsideringseedpointforneuralsurfacereconstruction