ControlGS: Consistent Structural Compression Control for Deployment-Aware Gaussian Splatting

TL;DR

ControlGS introduces a universal control framework for 3D Gaussian Splatting that dynamically balances rendering quality and model compression, enabling deployment across diverse scenes and device constraints.

Contribution

It proposes a scene-agnostic, continuous control mechanism for Gaussian count and quality trade-off, improving deployment flexibility and rendering performance.

Findings

Achieves higher rendering quality with fewer Gaussians.

Works effectively across various scene scales and complexities.

Provides a unified control hyperparameter for flexible model tuning.

Abstract

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/