GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting

Xianben Yang; Tao Wang; Yuxuan Li; Yi Jin; Haibin Ling

cs.CVApr 2, 2026

GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting

Authors: Xianben Yang, Tao Wang, Yuxuan Li, Yi Jin, Haibin Ling

Organizations: Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education; School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China · Department of Artificial Intelligence, Westlake University, Hangzhou 310030, China

Abstract

3D Gaussian Splatting (3DGS) has demonstrated breakthrough performance in novel view synthesis and real-time rendering. Nevertheless, its practicality is constrained by the high memory cost due to a huge number of Gaussian points. Many pruning-based 3DGS variants have been proposed for memory saving, but often compromise spatial consistency and may lead to rendering artifacts. To address this issue, we propose graph-based spatial distribution optimization for compact 3D Gaussian Splatting (GS\textasciicircum2), which enhances reconstruction quality by optimizing the spatial distribution of Gaussian points. Specifically, we introduce an evidence lower bound (ELBO)-based adaptive densification strategy that automatically controls the densification process. In addition, an opacity-aware progressive pruning strategy is proposed to further reduce memory consumption by dynamically removing low-opacity Gaussian points. Furthermore, we propose a graph-based feature encoding module to adjust the spatial distribution via feature-guided point shifting. Extensive experiments validate that GS\textasciicircum2 achieves a compact Gaussian representation while delivering superior rendering quality. Compared with 3DGS, it achieves higher PSNR with only about 12.5% Gaussian points. Furthermore, it outperforms all compared baselines in both rendering quality and memory efficiency.

Figures & tables

Panel of Figure 1 — Figure 1: Comparison of rendering quality and spatial distribution. We report the PSNR and number of Gaussian points ( $N_{\textrm{GS}}$ , in millions) for each method. While a SOTA solution (LightGaussian [ 6 ] ) compromises spatial consistency with visual artifacts, our method produces a more uniform and coherent distribution.

Figure 2: Comparison of rendering quality (PSNR) and number of Gaussian points (

N_{\textrm{GS}}

, in millions ) for various methods on the Mip-NeRF360 dataset.

Figure 3: The pipeline of our method. We propose an Adaptive Densification and Pruning (ADP) module that adaptively increases point density in phase 1 and prunes low-opacity points in phase 2. To improve the spatial distribution after pruning, we introduce a Graph-based Spatial Distribution Optimization (GSDO) module, which refines spatial distribution in phase 3 using a lightweight graph-based feature encoder with global alignment and local smoothness losses.

Figure 4: ELBO-guided adaptive densification.

Figure 5: Analyzing the impact of optimization. Low-opacity Gaussian points (

\text{opacity}\leq 0.1

) constitute a considerable portion of the total. For instance, in the Lighthouse scene from the Tanks & Temples dataset, they account for approximately 40% of all Gaussian points.

Panel of Figure 6 — Figure 6: Impact of pruning. We report PSNR and $N_{\textrm{GS}}$ (in millions) for each method on the church scene from Tanks & Temples. Pruning degrades the spatial consistency and continuity of the Gaussian points, leading to visible artifacts.

Dataset	Method	All Scenes				Outdoor				Indoor
Dataset	Method	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{\textrm{GS}}$ $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{\textrm{GS}}$ $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{\textrm{GS}}$ $\downarrow$
	3DGS	27.71	0.83	0.20	3.12	24.99	0.74	0.23	4.50	31.09	0.92	0.19	1.41
Mip-NeRF 360	EAGLES	27.22	0.82	0.23	1.25	24.64	0.73	0.27	1.69	30.46	0.93	0.18	0.71
	Mini-Splatting	27.34	0.82	0.22	0.49	24.71	0.74	0.24	0.57	30.61	0.92	0.19	0.40
	CompGS	27.25	0.82	0.23	0.86	24.79	0.73	0.26	1.19	30.33	0.92	0.19	0.46
	Compact 3DGS	27.25	0.81	0.23	1.35	24.61	0.72	0.27	1.47	30.54	0.92	0.18	1.21

Table 1: Quantitative rendering results of Mip-NeRF 360 and T&T. Bold font highlights the best results and underline for the second.

Panel of Figure 7 — Figure 7: Qualitative comparison. The first scene ( Room ) is from the Mip-NeRF 360 dataset, followed by four scenes ( Palace, Temple, Lighthouse, Courtroom ) from the Tanks & Temples dataset. Key regions have been zoomed in to highlight visual differences. We report the PSNR and $N_{\textrm{GS}}$ (in millions) for each method.

Dataset	Method	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{\textrm{GS}}$ $\downarrow$
Mip-NeRF 360	3DGS	27.71	0.83	0.20	3.12
	+ ELBO densification	27.73	0.83	0.20	2.82
	+ Opacity pruning	26.79	0.80	0.26	0.30
	+ Increase iterations	26.98	0.80	0.26	0.30
	+ $\mathcal{L}_{\text{smt}}$	27.53	0.81	0.25	0.30
	Full Model	27.74	0.82	0.23	0.30

Table 2: Ablation study. Evaluate the effectiveness of each component of our model on rendering quality.

Dataset	Method	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{\textrm{GS}}$ $\downarrow$
Mip-NeRF 360	LightGaussian	27.35	0.82	0.23	1.07
	(+GSDO)	27.75	0.82	0.21	1.07
	MaskGaussian	27.61	0.82	0.23	1.50
	(+GSDO)	27.94	0.83	0.20	1.50
T&T	LightGaussian	23.16	0.82	0.25	0.53
	(+GSDO)	23.97	0.83	0.22	0.53

Table 3: Integration of GSDO with other 3DGS variants.

Dataset	Method	Train Time (min) $\downarrow$	FPS $\uparrow$
T&T	3DGS	16	135
	EAGLES	21	247
	Mini-Splatting	14	576
	CompGS	17	325
	Compact 3DGS	27	345
	LightGaussian	17	214

Table 4: Training time and FPS comparison on T & T.

Dataset	Interval	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$
Mip-NeRF 360	100	27.74	0.82	0.23
	200	27.65	0.82	0.24
	400	27.60	0.82	0.24

Table 5: Ablation study for different pruning intervals.

3D Gaussian Splatting

3D Gaussian Splatting represents scenes as optimizable 3D Gaussian primitives for fast, photorealistic rendering from new viewpoints.

See all 986 papers

Prune Wisely, Reconstruct Sharply: Compact 3D Gaussian Splatting via Adaptive Pruning and Difference-of-Gaussian Primitives
Feb 27, 2026Haoran Wang, Guoxi Huang, Fan Zhang +23D Gaussian Splatting 3D Gaussian Pruning
School of Computer Science, University of Bristol, Bristol, UK
MMGS: 10 $\times$ Compressed 3DGS through Optimal Transport Aggregation based on Multi-view Ranking
May 19, 2026Beizhen Zhao, Sicheng Yu, Ziran Yin +23DGS Compression 3D Gaussian Splatting
The Hong Kong University of Science and Technology (Guangzhou)
EffGS: Efficient and High-Fidelity Gaussian Splatting
Sep 30, 2026Changbai Li, Shuo Yang, Yichen Yang +23D Gaussian Splatting 3D Gaussian Pruning
Beihang University · Nanyang Technological University

Feb 27, 2026J/K move · Enter open · S save

Prune Wisely, Reconstruct Sharply: Compact 3D Gaussian Splatting via Adaptive Pruning and Difference-of-Gaussian Primitives

Haoran Wang, Guoxi Huang, Fan Zhang, David Bull+1

School of Computer Science, University of Bristol, Bristol, UK

3D Gaussian Splatting 3D Gaussian Pruning 3DGS Compression

Open paper AskPDF arXiv

Recent significant advances in 3D scene representation have been driven by 3D Gaussian Splatting (3DGS), which has enabled real-time rendering with photorealistic quality. 3DGS often requires a large number of primitives to achieve high fidelity, leading to redundant representations and high resource consumption, thereby limiting its scalability for complex or large-scale scenes. Consequently, effective pruning strategies and more expressive primitives that can reduce redundancy while preserving visual quality are crucial for practical deployment. We propose an efficient, integrated reconstruction-aware pruning strategy that adaptively determines pruning timing and refining intervals based on reconstruction quality, thus reducing model size while enhancing rendering quality. Moreover, we introduce a 3D Difference-of-Gaussians primitive that jointly models both positive and negative densities in a single primitive, improving the expressiveness of Gaussians under compact configurations. Our method significantly improves model compactness, achieving up to 90% reduction in Gaussian-count while delivering visual quality that is similar to, or in some cases better than, that produced by state-of-the-art methods. Code will be made publicly available.

Abstract

3D Gaussian Splatting

Explore similar work

Prune Wisely, Reconstruct Sharply: Compact 3D Gaussian Splatting via Adaptive Pruning and Difference-of-Gaussian Primitives

MMGS: 10×\times× Compressed 3DGS through Optimal Transport Aggregation based on Multi-view Ranking

EffGS: Efficient and High-Fidelity Gaussian Splatting

MMGS: 10 $\times$ Compressed 3DGS through Optimal Transport Aggregation based on Multi-view Ranking