Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Fengdi, Sun, Yibao, Cao, Hongkun, Huang, Ruqi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.10473
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908634795999232
author Zhang, Fengdi
Sun, Yibao
Cao, Hongkun
Huang, Ruqi
author_facet Zhang, Fengdi
Sun, Yibao
Cao, Hongkun
Huang, Ruqi
contents 3D Gaussian Splatting (3DGS) is a highly deployable real-time method for novel view synthesis. In practice, it requires a universal, consistent control mechanism that adjusts the trade-off between rendering quality and model compression without scene-specific tuning, enabling automated deployment across different device performances and communication bandwidths. In this work, we present ControlGS, a control-oriented optimization framework that maps the trade-off between Gaussian count and rendering quality to a continuous, scene-agnostic, and highly responsive control axis. Extensive experiments across a wide range of scene scales and types (from small objects to large outdoor scenes) demonstrate that, by adjusting a globally unified control hyperparameter, ControlGS can flexibly generate models biased toward either structural compactness or high fidelity, regardless of the specific scene scale or complexity, while achieving markedly higher rendering quality with the same or fewer Gaussians compared to potential competing methods. Project page: https://zhang-fengdi.github.io/ControlGS/
format Preprint
id arxiv_https___arxiv_org_abs_2505_10473
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ControlGS: Consistent Structural Compression Control for Deployment-Aware Gaussian Splatting
Zhang, Fengdi
Sun, Yibao
Cao, Hongkun
Huang, Ruqi
Computer Vision and Pattern Recognition
3D Gaussian Splatting (3DGS) is a highly deployable real-time method for novel view synthesis. In practice, it requires a universal, consistent control mechanism that adjusts the trade-off between rendering quality and model compression without scene-specific tuning, enabling automated deployment across different device performances and communication bandwidths. In this work, we present ControlGS, a control-oriented optimization framework that maps the trade-off between Gaussian count and rendering quality to a continuous, scene-agnostic, and highly responsive control axis. Extensive experiments across a wide range of scene scales and types (from small objects to large outdoor scenes) demonstrate that, by adjusting a globally unified control hyperparameter, ControlGS can flexibly generate models biased toward either structural compactness or high fidelity, regardless of the specific scene scale or complexity, while achieving markedly higher rendering quality with the same or fewer Gaussians compared to potential competing methods. Project page: https://zhang-fengdi.github.io/ControlGS/
title ControlGS: Consistent Structural Compression Control for Deployment-Aware Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.10473