Saved in:
Bibliographic Details
Main Authors: Gao, Zhengqing, Hu, Dongting, Bian, Jia-Wang, Fu, Huan, Li, Yan, Liu, Tongliang, Gong, Mingming, Zhang, Kun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.17486
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912315638546432
author Gao, Zhengqing
Hu, Dongting
Bian, Jia-Wang
Fu, Huan
Li, Yan
Liu, Tongliang
Gong, Mingming
Zhang, Kun
author_facet Gao, Zhengqing
Hu, Dongting
Bian, Jia-Wang
Fu, Huan
Li, Yan
Liu, Tongliang
Gong, Mingming
Zhang, Kun
contents 3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis but is limited by the substantial number of Gaussian primitives required, posing challenges for deployment on lightweight devices. Recent methods address this issue by compressing the storage size of densified Gaussians, yet fail to preserve rendering quality and efficiency. To overcome these limitations, we propose ProtoGS to learn Gaussian prototypes to represent Gaussian primitives, significantly reducing the total Gaussian amount without sacrificing visual quality. Our method directly uses Gaussian prototypes to enable efficient rendering and leverage the resulting reconstruction loss to guide prototype learning. To further optimize memory efficiency during training, we incorporate structure-from-motion (SfM) points as anchor points to group Gaussian primitives. Gaussian prototypes are derived within each group by clustering of K-means, and both the anchor points and the prototypes are optimized jointly. Our experiments on real-world and synthetic datasets prove that we outperform existing methods, achieving a substantial reduction in the number of Gaussians, and enabling high rendering speed while maintaining or even enhancing rendering fidelity.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17486
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ProtoGS: Efficient and High-Quality Rendering with 3D Gaussian Prototypes
Gao, Zhengqing
Hu, Dongting
Bian, Jia-Wang
Fu, Huan
Li, Yan
Liu, Tongliang
Gong, Mingming
Zhang, Kun
Computer Vision and Pattern Recognition
Artificial Intelligence
3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis but is limited by the substantial number of Gaussian primitives required, posing challenges for deployment on lightweight devices. Recent methods address this issue by compressing the storage size of densified Gaussians, yet fail to preserve rendering quality and efficiency. To overcome these limitations, we propose ProtoGS to learn Gaussian prototypes to represent Gaussian primitives, significantly reducing the total Gaussian amount without sacrificing visual quality. Our method directly uses Gaussian prototypes to enable efficient rendering and leverage the resulting reconstruction loss to guide prototype learning. To further optimize memory efficiency during training, we incorporate structure-from-motion (SfM) points as anchor points to group Gaussian primitives. Gaussian prototypes are derived within each group by clustering of K-means, and both the anchor points and the prototypes are optimized jointly. Our experiments on real-world and synthetic datasets prove that we outperform existing methods, achieving a substantial reduction in the number of Gaussians, and enabling high rendering speed while maintaining or even enhancing rendering fidelity.
title ProtoGS: Efficient and High-Quality Rendering with 3D Gaussian Prototypes
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.17486