High-Fold 3D Gaussian Splatting Model Pruning Method Assisted by Opacity

Recent advancements in 3D scene representation have underscored the potential of Neural Radiance Fields (NeRFs) for producing high-fidelity renderings of complex scenes. However, NeRFs are hindered by the significant computational burden of volumetric rendering. To address this, 3D Gaussian Splattin...

Full description

Saved in:
Bibliographic Details
Main Authors: Shiyu Qiu, Chunlei Wu, Zhenghao Wan, Siyuan Tong
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/3/1535
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849717759183683584
author Shiyu Qiu
Chunlei Wu
Zhenghao Wan
Siyuan Tong
author_facet Shiyu Qiu
Chunlei Wu
Zhenghao Wan
Siyuan Tong
author_sort Shiyu Qiu
collection DOAJ
description Recent advancements in 3D scene representation have underscored the potential of Neural Radiance Fields (NeRFs) for producing high-fidelity renderings of complex scenes. However, NeRFs are hindered by the significant computational burden of volumetric rendering. To address this, 3D Gaussian Splatting (3DGS) has emerged as an efficient alternative, utilizing Gaussian-based representations and rasterization techniques to achieve faster rendering speeds without sacrificing image quality. Despite these advantages, the large number of Gaussian points and associated internal parameters result in high storage demands. To address this challenge, we propose a pruning strategy applied during the Gaussian densification and pruning phases. Our approach integrates learnable Gaussian masks with a contribution-based pruning mechanism, further enhanced by an opacity update strategy to facilitate the pruning process. This method effectively eliminates redundant Gaussian points and those with minimal contributions to scene construction. Additionally, during the Gaussian parameter compression phase, we employ a combination of teacher–student models and vector quantization to compress the spherical harmonic coefficients. Extensive experimental results demonstrate that our approach reduces the storage requirements of original 3D Gaussian models by over 30 times, with only a minor degradation in rendering quality.
format Article
id doaj-art-0c75ec19f91048478fd79d588b0ffc52
institution DOAJ
issn 2076-3417
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-0c75ec19f91048478fd79d588b0ffc522025-08-20T03:12:34ZengMDPI AGApplied Sciences2076-34172025-02-01153153510.3390/app15031535High-Fold 3D Gaussian Splatting Model Pruning Method Assisted by OpacityShiyu Qiu0Chunlei Wu1Zhenghao Wan2Siyuan Tong3Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266500, ChinaQingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266500, ChinaQingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266500, ChinaQingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266500, ChinaRecent advancements in 3D scene representation have underscored the potential of Neural Radiance Fields (NeRFs) for producing high-fidelity renderings of complex scenes. However, NeRFs are hindered by the significant computational burden of volumetric rendering. To address this, 3D Gaussian Splatting (3DGS) has emerged as an efficient alternative, utilizing Gaussian-based representations and rasterization techniques to achieve faster rendering speeds without sacrificing image quality. Despite these advantages, the large number of Gaussian points and associated internal parameters result in high storage demands. To address this challenge, we propose a pruning strategy applied during the Gaussian densification and pruning phases. Our approach integrates learnable Gaussian masks with a contribution-based pruning mechanism, further enhanced by an opacity update strategy to facilitate the pruning process. This method effectively eliminates redundant Gaussian points and those with minimal contributions to scene construction. Additionally, during the Gaussian parameter compression phase, we employ a combination of teacher–student models and vector quantization to compress the spherical harmonic coefficients. Extensive experimental results demonstrate that our approach reduces the storage requirements of original 3D Gaussian models by over 30 times, with only a minor degradation in rendering quality.https://www.mdpi.com/2076-3417/15/3/15353D gaussian splattingnovel view synthesis3D compression
spellingShingle Shiyu Qiu
Chunlei Wu
Zhenghao Wan
Siyuan Tong
High-Fold 3D Gaussian Splatting Model Pruning Method Assisted by Opacity
Applied Sciences
3D gaussian splatting
novel view synthesis
3D compression
title High-Fold 3D Gaussian Splatting Model Pruning Method Assisted by Opacity
title_full High-Fold 3D Gaussian Splatting Model Pruning Method Assisted by Opacity
title_fullStr High-Fold 3D Gaussian Splatting Model Pruning Method Assisted by Opacity
title_full_unstemmed High-Fold 3D Gaussian Splatting Model Pruning Method Assisted by Opacity
title_short High-Fold 3D Gaussian Splatting Model Pruning Method Assisted by Opacity
title_sort high fold 3d gaussian splatting model pruning method assisted by opacity
topic 3D gaussian splatting
novel view synthesis
3D compression
url https://www.mdpi.com/2076-3417/15/3/1535
work_keys_str_mv AT shiyuqiu highfold3dgaussiansplattingmodelpruningmethodassistedbyopacity
AT chunleiwu highfold3dgaussiansplattingmodelpruningmethodassistedbyopacity
AT zhenghaowan highfold3dgaussiansplattingmodelpruningmethodassistedbyopacity
AT siyuantong highfold3dgaussiansplattingmodelpruningmethodassistedbyopacity