GoDe: Gaussians on Demand for Progressive Level of Detail and Scalable Compression

TL;DR

GoDe introduces a scalable, progressive compression framework for 3D Gaussian Splatting that reorganizes primitives into a hierarchy, enabling multiple quality levels from a single trained model without retraining.

Contribution

It presents GoDe, a novel method for intrinsic scalability in 3D Gaussian models, allowing multiple compression levels from one trained model using a structured primitive hierarchy.

Findings

Achieves rate-distortion performance comparable to state-of-the-art single-rate methods.

Enables scalable compression and adaptive rendering without retraining.

Supports multiple operating points from a single model.

Abstract

Recent progress in compressing explicit radiance field representations, particularly 3D Gaussian Splatting, has substantially reduced memory consumption while improving real-time rendering performance. However, existing approaches remain inherently single-rate: each compression level requires a separately optimized model, yielding a set of fixed operating points rather than a truly scalable representation. This limits deployment in scenarios where memory, bandwidth, or computational budgets vary across devices or over time. We argue that scalability should be an intrinsic property of the representation. We show that trained explicit radiance models exhibit a structured distribution of information, which can be revealed using standard optimization signals available during training. In particular, aggregated gradient sensitivity provides a simple, model-agnostic criterion to organize primitives from coarse structure to finer refinements. Building on this, we introduce GoDe (Gaussians on Demand), a general framework for scalable compression and progressive level-of-detail control, instantiated for 3D Gaussian Splatting. Starting from a single trained model, GoDe reorganizes Gaussian primitives into a fixed progressive hierarchy supporting multiple rate-distortion operating points without retraining or per-level fine-tuning. A single quantization-aware fine-tuning stage ensures consistent behavior across all levels under low-precision storage. Extensive experiments on standard benchmarks and multiple 3D Gaussian Splatting backbones show that GoDe achieves rate-distortion performance comparable to state-of-the-art single-rate methods, while enabling truly scalable compression and adaptive rendering within a unified representation. Project page: https://gaussians-on-demand.github.io