Fast mesh denoising with data driven normal filtering using deep variational autoencoders
| Main Authors: | Stavros Nousias, Gerasimos Arvanitis, Aris S. Lalos, Konstantinos Moustakas |
|---|---|
| Format: | Article eJournal |
| Terbitan: |
, 2020
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/3865275 |
| ctrlnum |
3865275 |
|---|---|
| fullrecord |
<?xml version="1.0"?>
<dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd"><creator>Stavros Nousias</creator><creator>Gerasimos Arvanitis</creator><creator>Aris S. Lalos</creator><creator>Konstantinos Moustakas</creator><date>2020-05-29</date><description>Recent advances in 3D scanning technology have enabled the deployment of 3D models in various industrial applications like digital twins, remote inspection and reverse engineering. Despite their evolving performance, 3D scanners, still introduce noise and artifacts in the acquired dense models. In this work, we propose a fast and robust denoising method for dense 3D scanned industrial models. The proposed approach employs conditional variational autoencoders to effectively filter face normals. Training and inference are performed in a sliding patch setup reducing the size of the required training data and execution times. We conducted extensive evaluation studies using 3D scanned and CAD models. The results verify plausible denoising outcomes, demonstrating similar or higher reconstruction accuracy, compared to other state-of-the-art approaches. Specifically, for 3D models with more than 1e4 faces, the presented pipeline is twice as fast as methods with equivalent reconstruction error.</description><identifier>https://zenodo.org/record/3865275</identifier><identifier>10.5281/zenodo.3865275</identifier><identifier>oai:zenodo.org:3865275</identifier><relation>info:eu-repo/grantAgreement/EC/H2020/777981/</relation><relation>doi:10.5281/zenodo.3865274</relation><relation>url:https://zenodo.org/communities/warmest</relation><rights>info:eu-repo/semantics/openAccess</rights><rights>https://creativecommons.org/licenses/by/4.0/legalcode</rights><source>IEEE Transactions on Industrial Informatics</source><subject>3D mesh denoising, data driven normal filtering, variational autoencoders</subject><title>Fast mesh denoising with data driven normal filtering using deep variational autoencoders</title><type>Journal:Article</type><type>Journal:Article</type><recordID>3865275</recordID></dc>
|
| format |
Journal:Article Journal Journal:eJournal |
| author |
Stavros Nousias Gerasimos Arvanitis Aris S. Lalos Konstantinos Moustakas |
| title |
Fast mesh denoising with data driven normal filtering using deep variational autoencoders |
| publishDate |
2020 |
| topic |
3D mesh denoising data driven normal filtering variational autoencoders |
| url |
https://zenodo.org/record/3865275 |
| contents |
Recent advances in 3D scanning technology have enabled the deployment of 3D models in various industrial applications like digital twins, remote inspection and reverse engineering. Despite their evolving performance, 3D scanners, still introduce noise and artifacts in the acquired dense models. In this work, we propose a fast and robust denoising method for dense 3D scanned industrial models. The proposed approach employs conditional variational autoencoders to effectively filter face normals. Training and inference are performed in a sliding patch setup reducing the size of the required training data and execution times. We conducted extensive evaluation studies using 3D scanned and CAD models. The results verify plausible denoising outcomes, demonstrating similar or higher reconstruction accuracy, compared to other state-of-the-art approaches. Specifically, for 3D models with more than 1e4 faces, the presented pipeline is twice as fast as methods with equivalent reconstruction error. |
| id |
IOS17403.3865275 |
| institution |
Universitas PGRI Palembang |
| institution_id |
189 |
| institution_type |
library:university library |
| library |
Perpustakaan Universitas PGRI Palembang |
| library_id |
587 |
| collection |
Marga Life in South Sumatra in the Past: Puyang Concept Sacrificed and Demythosized |
| repository_id |
17403 |
| city |
KOTA PALEMBANG |
| province |
SUMATERA SELATAN |
| repoId |
IOS17403 |
| first_indexed |
2022-07-26T01:36:31Z |
| last_indexed |
2022-07-26T01:36:31Z |
| recordtype |
dc |
| _version_ |
1739406794811244544 |
| score |
17.608969 |