FilterGS: Traversal-Free Parallel Filtering and Adaptive Shrinking for Large-Scale LoD 3D Gaussian Splatting

Yixian Wang; Haolin Yu; Jiadong Tang; Yu Gao; Xihan Wang; Yufeng Yue; Yi Yang

cs.CVMar 25, 2026

FilterGS: Traversal-Free Parallel Filtering and Adaptive Shrinking for Large-Scale LoD 3D Gaussian Splatting

Authors: Yixian Wang, Haolin Yu, Jiadong Tang, Yu Gao, Xihan Wang, Yufeng Yue, Yi Yang

Organizations: Beijing Institute of Technology

Abstract

3D Gaussian Splatting has revolutionized neural rendering with real-time performance. However, scaling this approach to large scenes using Level-of-Detail methods faces critical challenges: inefficient serial traversal consuming over 60% of rendering time, and redundant Gaussian-tile pairs that incur unnecessary processing overhead. To address these limitations, we introduce FilterGS, featuring a parallel filtering mechanism with two complementary filters that select Gaussian elements efficiently without tree traversal. Additionally, we propose a novel GTC metric that quantifies the redundancy of Gaussian-tile key-value pairs. Based on this metric, we introduce a scene-adaptive Gaussian shrinking strategy that effectively reduces redundant pairs. Extensive experiments demonstrate that FilterGS achieves state-of-the-art rendering speeds while maintaining competitive visual quality across multiple large-scale datasets. Project page: https://github.com/xenon-w/FilterGS

Figures & tables

Figure 2: The framework of FilterGS . (a) Given a set of images and SfM points for a large-scale scene, we first train a LoD-GS tree model. (Sec. 3.1 ) (b) To quantify redundancy of scene-wide Gaussian-tile pairs, we perform a pre-rendering pass over all training views. While following the standard 3DGS pipeline, this stage computes the GTC metric $\bar{G}$ and derives a shrinking threshold $\tau=f(\bar{G})$ . (Sec. 3.3 ) (c) In the formal rendering stage, the pre-computed scaling factor $\tau$ and the tree model are processed by two specialized filters to efficiently select Gaussians for rendering. These Gaussians are adaptively scaled by $\tau$ during AABB formation, significantly reducing redundant key-value pairs before final sorting and $\alpha$ -blending. (Sec. 3.2 )

Figure 3: Comparison of serial and parallel filtering strategies. LoG starts from level=0 and progressively applies R&C rules to filter internal nodes with oversized 2D radii and child nodes, retaining only leaves or sufficiently small internal nodes. In contrast, FilterGS simultaneously applies the R&L Filter across all levels to preserve nodes with small 2D radii and all leaf nodes, while introducing an Ancestor Filter to exclude nodes whose ancestor paths contain qualified internal nodes. This yields a key advantage: while LoG’s serial filtering requires steps proportional to tree depth (more levels, more steps), FilterGS completes parallel filtering in just two steps (No more levels, no matter levels).

Figure 4: Schematic Diagram of the Progressive Relationship Between the Four Core Formulas (Eqa. 5 , 6 , 7 , 8 ) of Sec. 3.3 .


Method	Block Small [ 12 ]					Sci-Art [ 15 ]					Residence [ 15 ]
Method	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$t_{\text{f}}$ $\downarrow$	FPS $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$t_{\text{f}}$ $\downarrow$	FPS $\uparrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$t_{\text{f}}$ $\downarrow$	FPS $\uparrow$
3DGS	25.42	0.743	0.446	–	58.0	22.35	0.717	0.311	–	61.0	21.92	0.767	0.298	–	62.0
H3DGS	25.73	0.756	0.440	5.51	83.0	22.41	0.719	0.312	53.46	72.0	21.99	0.769	0.294	7.12	38.0
LoG	26.52	0.770	0.414	10.46	77.0	23.27	0.737	0.305	11.6	67.0	22.7	0.812	0.267	11.33	66.0
OctreeGS	26.43	0.771	0.417	5.13	125.0	23.81	0.758	0.295	6.78	83.0	22.31	0.793	0.279	5.58	91.0

Table 1: Quantitative results on MatrixCity [ 12 ] , UrbanScene [ 15 ] and GauUScene [ 32 ] dataset. The 1st , 2nd and 3rd best results are highlighted. Our method achieves state-of-the-art rendering FPS by reducing filter time

t_{f}

(ms) and employing the Gaussian shrinking strategy, maintaining high-fidelity reconstruction quality competitive with the top-performing approaches.

Panel of Figure 5 — Figure 5: Comparison of Different Shrinking Strategy on College and Modern-Building [ 32 ] . The best results are highlighted in bold . $N_{P}$ represents the total number of generated key-value pairs. (a) to (d) show the rendered detail: (a) vanilla 3DGS ( $3\sigma$ principle); (b) 3DGS with our shrinking strategy ( $\lambda_{G}=0.2$ ); (c) FilterGS with the $3\sigma$ principle; (d) FilterGS with $\lambda_{G}=0.2$ .

Shrink	Filter	$T_{\text{calcu.}}$	$T_{\text{synch.}}$	$T_{\text{prepr.}}$	$T_{\text{sort~}}$	$T_{\text{alpha}}$	$T_{\text{total}}$	FPS
✗	✗	3.59	7.72	0.20	1.04	2.58	15.13	66
✓	✗	3.59	7.80	0.27	0.61	1.69	13.96	72
✗	✓	0.52	0.41	0.19	1.01	2.64	4.77	210
✓	✓	0.52	0.40	0.26	0.57	1.62	3.37	297

Table 2: Ablation Study about Rendering Time Cost (ms) on Residence [ 15 ] . The best results are highlighted in bold . The total rendering time (

T_{\text{total}}

) is divided into four phases: Gaussian filtering (

T_{\text{calcu.}}+T_{\text{synch.}}

), preprocessing (

T_{\text{prepr.}}

), sorting (

T_{\text{sort}}

), and

\alpha

-blending (

T_{\text{alpha}}

		College			Modern
Shrink	Filter	PSNR	SSIM	${N_{P}}$ $\downarrow$	PSNR	SSIM	$N_{P}$ $\downarrow$
✗	✗	25.90	0.752	3.25M	27.35	0.813	2.13M
✓	✗	25.69	0.748	1.56M	27.04	0.810	1.12M
✗	✓	25.90	0.752	3.25M	27.35	0.813	2.13M
✓	✓	25.69	0.748	1.56M	27.04	0.810	1.12M

Table 3: Ablation Study about Rendering Quality on College [ 32 ] and Modern-Building [ 32 ] .

N_{P}

represents the total number of generated key-value pairs.

Figure 6: (a). The Trade-off between PSNR and FPS versus $\lambda_{G}$ . (b). Distribution of Key-Value Pairs as a Function of KPC, with (w/) and without (w/o) the shrinking. ( $\lambda_{G}=0.2$ , scene: Residence [ 15 ] )

Panel of Figure 7 — Figure 7: Effect of $\lambda_{G}$ on Key-Value Pair Pruning and Rendering Detail on Block [ 12 ] and Residence [ 32 ] . $N_{\text{low}}$ represents the number (M) of KPC $<0.01$ pairs.

Explore similar work

BlitzGS: City-Scale Gaussian Splatting at Lightning Speed
May 13, 2026Zhongtao Wang, Huishan Au, Yilong Li +63D Gaussian Splatting 3D Gaussian Pruning
Peking University, China
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
AdaGScale: Viewpoint-Adaptive Gaussian Scaling in 3D Gaussian Splatting to Reduce Gaussian-Tile Pairs
Apr 21, 2026Joongho Jo, Hyerin Lim, Hanjun Choi +13D Gaussian Splatting 3DGS Acceleration
Korea University Seoul, Republic of Korea

May 13, 2026J/K move · Enter open · S save

BlitzGS: City-Scale Gaussian Splatting at Lightning Speed

Zhongtao Wang, Huishan Au, Yilong Li, Mai Su+5

Peking University, China

3D Gaussian Splatting 3D Gaussian Pruning 3DGS Acceleration GPU Acceleration 3D Reconstruction Gaussian Splatting

Open paper AskPDF arXiv

We present BlitzGS, a distributed 3DGS framework that reduces active Gaussian workload for fast city-scale reconstruction. BlitzGS manages this workload at three coupled levels. At the system level, the framework shards Gaussians across GPUs by index parity rather than spatial blocks. This approach mitigates the cross-block visibility redundancy inherent in spatial partitioning. Furthermore, it distributes each rendering step through a single cross-GPU exchange that routes projected Gaussians to their tile owners. At the model level, scheduled importance-scoring passes shrink the global Gaussian population. During these passes, the framework generates a per-Gaussian visibility weight to bias density-control updates toward contributing primitives and a per-view importance mask for the view-level renderer. At the view level, BlitzGS trims each camera's active set with a distance-based LOD gate to exclude excessively fine primitives for the current frustum and the importance-based culling mask to skip Gaussians with negligible cross-view contribution. On large-scale benchmarks, BlitzGS matches the rendering quality of recent large-scale baselines while delivering an order-of-magnitude speedup, training city-scale scenes in tens of minutes. Our code is available at https: //github.com/AkierRaee/BlitzGS.

Abstract

Explore similar work

BlitzGS: City-Scale Gaussian Splatting at Lightning Speed

EffGS: Efficient and High-Fidelity Gaussian Splatting

AdaGScale: Viewpoint-Adaptive Gaussian Scaling in 3D Gaussian Splatting to Reduce Gaussian-Tile Pairs