EffGS: Efficient and High-Fidelity Gaussian Splatting

Changbai Li; Shuo Yang; Yichen Yang; Shuwei Shao; Huobin Tan

cs.CVSep 30, 2026

EffGS: Efficient and High-Fidelity Gaussian Splatting

Authors: Changbai Li, Shuo Yang, Yichen Yang, Shuwei Shao, Huobin Tan

Organizations: Beihang University · Nanyang Technological University

Abstract

3D Gaussian Splatting (3DGS) enables real-time novel view synthesis, but existing general-purpose acceleration methods suffer severe rendering quality degradation when extended to more complex, large-scale scenes. To address this issue, we propose EffGS, a more general acceleration framework that improves training and rendering efficiency while maintaining reconstruction quality comparable to or better than vanilla 3DGS across bounded and large-scale scenes. EffGS combines frequency-aware guidance, localized density control, and adaptive primitive scale modulation. First, an importance scoring mechanism combines pixel-wise reconstruction errors with a difference-of-Gaussians mask scheduled over training to provide stage-dependent spatial guidance. Second, localized densification and pruning restricts density modifications to Gaussians with valid projected footprints in the sampled views. Third, learnable per-Gaussian scale modulation adjusts effective primitive extent during optimization while retaining the Compact Box rasterization rule. Extensive experiments on bounded and large-scale scene datasets demonstrate a favorable balance between reconstruction quality, training time, and primitive count. Component ablations and matched-primitive-budget comparisons further support the effectiveness of the framework.

Figures & tables

Figure 1: Compared with existing 3DGS acceleration methods, they can maintain high-quality rendering in small-scale scenes but suffer from degraded rendering quality when scaled up to city-level scenarios. In contrast, EffGS sustains high-fidelity rendering consistently, demonstrating superior scalability.

Figure 2: Spectral magnitude errors (left) and high-frequency discrepancy visualizations with ground-truth references (right) on Building ( Turki et al., 2022b ) ; see Sec. A.4 .

Figure 3: Overview of the proposed unified optimization pipeline. Given a set of sampled views, we first identify the visible Gaussians. We then compute a unified 2D supervision signal by fusing a pixel-wise error-aware mask with a frequency-aware mask (extracted via an annealing schedule). Finally, we project the visible Gaussians to 2D to accumulate importance scores from the unified mask, guiding localized densification and pruning.

Figure 4: Learnable primitive compactness. Compared with vanilla 3DGS ( Kerbl et al., 2023 ) , Speedy-Splat ( Hanson et al., 2025a ) , and FastGS ( Ren et al., 2025 ) , our method learns per-Gaussian compactness, reducing redundant pairs and improving fidelity.

Figure 5: Qualitative results of ours and other methods in image rendering on Deep Blending ( Park et al., 2019 ) , Mip-NeRF 360 ( Barron et al., 2022 ) and Tanks & Temples datasets ( Knapitsch et al., 2017 ) .

Figure 6: Qualitative results of ours and other methods in image rendering on Mill-19 ( Turki et al., 2022b ) , Urbanscene3D ( Lin et al., 2022 ) and GauU-Scene datasets ( Xiong et al., 2024 ) .

Method	Mip-NeRF 360						Deep Blending						Tanks & Temples
Method	Time $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{GS}$ $\downarrow$	FPS $\uparrow$	Time $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{GS}$ $\downarrow$	FPS $\uparrow$	Time $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{GS}$ $\downarrow$	FPS $\uparrow$
3DGS	20.93	27.53	0.812	0.221	2.63M	146	19.77	29.71	0.903	0.241	2.46M	158	11.34	23.71	0.850	0.170	1.57M	195
3DGS-LM	10.37	27.42	0.810	0.222	3.36M	220	9.83	29.61	0.905	0.248	2.71M	248	6.15	23.53	0.842	0.184	1.81M	289
Mini-Splatting	14.67	27.32	0.821	0.217	0.53M	567	13.35	29.99	0.907	0.244	0.56M	624	9.06	23.46	0.844	0.181	0.30M	756
Speedy-Splat	13.38	26.91	0.781	0.295	0.30M	552	10.75	29.42	0.898	0.272	0.25M	664	6.32	23.38	0.816	0.242	0.18M	691
Taming-3DGS	5.14	27.48	0.794	0.261	0.68M	221	3.06	29.50	0.894	0.278	0.29M	352	2.71	23.89	0.833	0.214	0.32M	379

Table 1: Quantitative comparison on Mip-NeRF 360 ( Barron et al., 2022 ) , Deep Blending ( Hedman et al., 2018 ) , and Tanks & Temples ( Knapitsch et al., 2017 ) .

Method	Mill-19						UrbanScene3D						GauU-Scene
Method	Time (m) $\downarrow$	SSIM $\uparrow$	PSNR $\uparrow$	LPIPS $\downarrow$	$N_{GS}$ $\downarrow$	FPS $\uparrow$	Time (m) $\downarrow$	SSIM $\uparrow$	PSNR $\uparrow$	LPIPS $\downarrow$	$N_{GS}$ $\downarrow$	FPS $\uparrow$	Time (m) $\downarrow$	SSIM $\uparrow$	PSNR $\uparrow$	LPIPS $\downarrow$	$N_{GS}$ $\downarrow$	FPS $\uparrow$
3DGS	196	0.735	23.06	0.292	10.76	$<50$	180	0.763	21.69	0.252	6.12	$<50$	176	0.736	23.66	0.268	6.58	$<50$
PGSR	212	0.603	20.12	0.447	12.41	$<50$	177	0.780	20.01	0.285	5.87	$<50$	187	0.593	20.57	0.421	5.98	$<50$
Mip-Splatting	187	0.703	22.35	0.334	18.44	$<50$	192	0.775	21.37	0.266	13.07	$<50$	184	0.660	21.40	0.341	14.50	$<50$
Taming-3DGS	21	0.551	21.22	0.510	0.75	88	23	0.633	19.74	0.460	0.48	73	29	0.714	23.77	0.308	5.92	84
Speedy-Splat	45	0.522	19.70	0.547	0.54	204	54	0.658	19.52	0.432	0.56	181	45	0.646	22.42	0.401	0.73	185

Table 2: Quantitative comparison of the averaged metrics on Mill-19 ( Turki et al., 2022b ) , UrbanScene3D ( Lin et al., 2022 ) , and GauU-Scene ( Xiong et al., 2024 ) .

Ablation Item	Rendering Quality			Efficiency Metrics
Ablation Item	SSIM $\uparrow$	PSNR $\uparrow$	LPIPS $\downarrow$	Time (Min) $\downarrow$	Size (GB) $\downarrow$	GS (M) $\downarrow$	Mem (G) $\downarrow$
(a) w/o Frequency-aware Mask	0.752	24.12	0.278	22	1.15	4.51	15.6
(b) w/o Error-aware Mask	0.748	23.98	0.284	21	1.23	4.42	14.8
(c) w/o Learnable Compactness ( $\gamma_{i}$ )	0.745	23.85	0.288	28	1.25	4.98	16.5
(d) w/o Local Densification and Pruning (LDP)	0.741	23.75	0.295	19	0.98	3.85	14.2
(e) w/o Frequency-aware Loss ( $\mathcal{L}_{freq}$ )	0.753	24.16	0.276	19	1.05	4.20	15.3

Table 3: Component ablations on GauU-Scene ( Xiong et al., 2024 ) , evaluating reconstruction quality and computational cost.

Appendix figures & tables21 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 7: Low-, mid-, and high-frequency spectral magnitude errors across scenes.

Method	Bicycle	Flowers	Garden	Stump	Treehill	Room	Counter	Kitchen	Bonsai
3DGS	25.14	21.30	27.34	26.64	22.59	31.71	29.16	31.54	32.37
Mini-Splatting	25.23	21.43	27.36	26.80	22.76	31.48	28.65	31.05	31.24
Speedy-Splat	24.79	21.21	26.69	26.67	22.48	30.83	28.22	30.09	31.16
Taming-3DGS	24.72	21.10	27.42	26.05	22.92	31.64	29.20	31.84	32.40
DashGaussian	25.31	21.78	27.57	27.17	22.94	31.81	29.11	31.69	32.15
FastGS	24.84	21.21	27.20	26.65	22.94	31.98	29.15	31.87	32.19

Appendix

Table 4: Quantitative PSNR comparison on Mip-NeRF 360 ( Barron et al., 2022 ) . The best, second-best, and third-best results are indicated by light red, light orange, and light yellow backgrounds, respectively.

Figure 8: Band-wise spectral magnitude errors over 30,000 training iterations on Rubble.

Method	Bicycle	Flowers	Garden	Stump	Treehill	Room	Counter	Kitchen	Bonsai
3DGS	0.748	0.586	0.857	0.768	0.636	0.927	0.915	0.932	0.946
Mini-Splatting	0.764	0.614	0.806	0.839	0.656	0.928	0.911	0.930	0.943
Speedy-Splat	0.704	0.560	0.814	0.765	0.590	0.903	0.876	0.895	0.925
Taming-3DGS	0.693	0.552	0.851	0.729	0.628	0.917	0.909	0.929	0.942
DashGaussian	0.763	0.604	0.857	0.783	0.640	0.924	0.911	0.927	0.945
FastGS	0.714	0.560	0.836	0.756	0.612	0.920	0.907	0.929	0.942

Appendix

Table 5: Quantitative SSIM comparison on Mip-NeRF 360 ( Barron et al., 2022 ) . The best, second-best, and third-best results are indicated by light red, light orange, and light yellow backgrounds, respectively.

Method	Bicycle	Flowers	Garden	Stump	Treehill	Room	Counter	Kitchen	Bonsai
3DGS	0.242	0.360	0.122	0.244	0.347	0.197	0.183	0.116	0.180
Mini-Splatting	0.241	0.341	0.215	0.161	0.326	0.190	0.181	0.120	0.177
Speedy-Splat	0.333	0.418	0.214	0.288	0.462	0.258	0.259	0.195	0.228
Taming-3DGS	0.332	0.416	0.138	0.324	0.395	0.227	0.200	0.128	0.193
DashGaussian	0.222	0.341	0.131	0.229	0.333	0.205	0.191	0.129	0.180
FastGS	0.310	0.406	0.174	0.297	0.429	0.217	0.204	0.127	0.191

Appendix

Table 6: Quantitative LPIPS comparison on Mip-NeRF 360 ( Barron et al., 2022 ) . The best, second-best, and third-best results are indicated by light red, light orange, and light yellow backgrounds, respectively.

Method	bicycle	flowers	garden	stump	treehill	room	counter	kitchen	bonsai
3DGS	27.97	18.98	26.78	21.77	20.33	18.78	17.58	21.30	14.90
Mini-Splatting	16.17	17.22	15.97	16.52	17.05	18.00	9.83	10.23	11.02
Speedy-Splat	15.87	13.38	15.73	13.77	12.90	12.05	12.10	13.25	11.37
Taming-3DGS	5.65	4.97	9.82	3.93	5.37	3.88	4.60	3.48	4.60
DashGaussian	9.93	7.05	8.27	6.57	8.20	4.00	3.95	5.52	3.95
FastGS	1.92	1.95	2.47	1.72	1.72	1.62	1.83	2.42	1.83

Appendix

Table 7: Quantitative results (Time) on Mip-NeRF 360 ( Barron et al., 2022 ) .

Method	Mill-19		UrbanScene3D		GauU-Scene
Method	Building	Rubble	Residence	Sci-Art	Russian Building	Residence+	Modern Building
VastGaussian $\dagger$	0.725	0.745	0.712	0.765	0.781	0.738	0.789
CityGaussian	0.776	0.814	0.810	0.835	0.801	0.755	0.791
CityGS-v2	0.661	0.724	0.771	0.808	0.792	0.741	0.762
CityGS-X*	0.771	0.803	0.802	0.829	0.793	0.742	0.774
3DGS	0.722	0.748	0.782	0.743	0.770	0.686	0.751

Appendix

Table 8: Quantitative SSIM comparison (

\uparrow

) across different datasets. Building and Rubble are from Mill-19 ( Turki et al., 2022b ) ; Residence and Sci-Art are from UrbanScene3D ( Lin et al., 2022 ) ; Russian Building, Residence+, and Modern Building are from GauU-Scene ( Xiong et al., 2024 ) . The best, second-best, and third-best results are indicated by light red, light orange, and light yellow backgrounds, respectively.

\dagger

denotes results obtained without decoupled appearance encoding, while * denotes results obtained without depth supervision.

Figure 9: Quantitative comparison of computational overhead on the Mill-19 ( Turki et al., 2022b ) , Urbanscene3D ( Lin et al., 2022 ) , and GauU-Scene datasets ( Xiong et al., 2024 ) . ∗ indicates multi-GPU training.

Method	Mill-19		UrbanScene3D		GauU-Scene
Method	Building	Rubble	Residence	Sci-Art	Russian Building	Residence+	Modern Building
VastGaussian $\dagger$	21.83	25.24	21.06	22.59	23.98	23.41	25.53
CityGaussian	21.56	25.79	22.03	22.42	24.11	23.65	26.01
CityGS-v2	19.85	24.02	21.23	20.71	24.04	23.43	25.78
CityGS-X*	21.78	25.45	22.11	22.32	24.18	23.91	25.95
3DGS	20.62	25.49	21.45	21.92	23.74	22.10	25.15

Appendix

Table 9: Quantitative PSNR comparison (

\uparrow

\dagger

denotes results obtained without decoupled appearance encoding, while * denotes results obtained without depth supervision.

Figure 10: Visualization of the frequency-aware mask at different schedule parameters $f$ on a fixed input image. Top: continuous mask scores before thresholding. Middle: score heatmaps overlaid on the input. Bottom: binary masks obtained with a threshold of 0.5, where white indicates selected pixels. Scores are normalized independently for each setting.

Figure 11: Peak VRAM usage (top) and step-wise changes (bottom) during frequency extraction with varying resolutions and batch size 10 on Russian ( Xiong et al., 2024 ) .

Figure 12: Qualitative comparisons on the Mill-19, Urbanscene3D, and GauU-Scene datasets ( Turki et al., 2022b ; Lin et al., 2022 ; Xiong et al., 2024 ) .

Figure 13: Qualitative comparisons on the Deep Blending, Mip-NeRF 360, and Tanks & Temples datasets ( Park et al., 2019 ; Barron et al., 2022 ; Knapitsch et al., 2017 ) .

Method	Mill-19		UrbanScene3D		GauU-Scene
Method	Building	Rubble	Residence	Sci-Art	Russian Building	Residence+	Modern Building
VastGaussian $\dagger$	0.271	0.268	0.263	0.259	0.251	0.301	0.245
CityGaussian	0.267	0.226	0.213	0.232	0.223	0.289	0.253
CityGS-v2	0.382	0.311	0.235	0.265	0.234	0.294	0.254
CityGS-X*	0.256	0.224	0.221	0.241	0.220	0.284	0.234
3DGS	0.304	0.279	0.238	0.265	0.234	0.321	0.249

Appendix

Table 10: Quantitative LPIPS comparison (

\downarrow

\dagger

denotes results obtained without decoupled appearance encoding, while * denotes results obtained without depth supervision.

Figure 14: Quantitative comparison of computational overhead on the Deep Blending ( Park et al., 2019 ) , Mip-NeRF 360 ( Barron et al., 2022 ) , and Tanks & Temples datasets ( Knapitsch et al., 2017 ) .

Method	SSIM $\uparrow$	PSNR $\uparrow$	LPIPS $\downarrow$
FastGS	0.741	23.48	0.294
FastGS+LDP	0.758	23.89	0.257

Appendix

Table 11: Ablation study on the Russian scene from the GauU-Scene dataset ( Xiong et al., 2024 ) .

Method	Residence+			Russian Building			Modern Building
Method	Time (min)	GS (M)	FPS	Time (min)	GS (M)	FPS	Time (min)	GS (M)	FPS
CityGaussian	261	8.14	68	214	7.02	55	217	7.90	57
CityGS-v2	203	8.04	46	182	6.97	33	188	7.90	35
Speedy-splat	50	0.50	195	43	0.82	189	43	0.87	170
FastGS	14	2.91	252	12	1.89	231	12	2.23	224
EffGS	19	4.86	131	21	3.45	127	23	4.37	115

Appendix

Table 12: Efficiency comparison on Residence+, Russian Building, and Modern Building scenes from the GauU-Scene dataset ( Xiong et al., 2024 ) .

Uncontrolled Gaussian‑point count
Method	Deep Blending					Tanks & Temples
Method	Time $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{\mathrm{GS}}$	Time $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{\mathrm{GS}}$
EDGS	30.00	29.81	0.904	0.223	–	23.00	24.28	0.868	0.132	–
3DGS-MCMC	19.00	29.56	0.902	0.244	–	13.00	24.22	0.863	0.158	–
EffGS (Ours)	2.94	30.01	0.910	0.238	0.25	1.94	24.22	0.861	0.166	0.44
Matched Gaussian budgets: controlled comparison

Appendix

Table 13: Comparison on Deep Blending and Tanks & Temples. Top: reported settings. Bottom: Gaussian budgets matched to EffGS. Time is in minutes and

N_{\mathrm{GS}}

in millions; – denotes unavailable counts. Best quality and timing results within each block and dataset are bold.

Method	Mill-19					UrbanScene3D
Method	Time $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{\mathrm{GS}}$	Time $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{\mathrm{GS}}$
Taming-3DGS	57	22.52	0.693	0.384	3.76	61	21.14	0.719	0.332	3.05
EDGS+3DGS	83	22.57	0.716	0.372	3.76	91	21.17	0.716	0.330	3.05
EffGS (Ours)	20	23.68	0.755	0.279	3.76	22	21.50	0.778	0.281	3.05

Appendix

Table 14: Matched-budget comparison on Mill-19 and UrbanScene3D. EDGS+3DGS uses matched initialization with densification disabled. Time is in minutes and

N_{\mathrm{GS}}

in millions. Best quality and timing results are bold.

Method	Frequency Error			Reconstruction Quality			$N_{\mathrm{GS}}$ $\downarrow$
Method	Low $\downarrow$	Mid $\downarrow$	High $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$N_{\mathrm{GS}}$ $\downarrow$
w/o Learnable Compactness ( $\gamma_{i}$ )	86726.7	30836.8	7073.6	26.99	0.810	0.264	2.30
EffGS (Ours)	72713.2	25773.5	5678.1	28.51	0.855	0.194	2.02

Appendix

Table 15: Extended ablation of learnable primitive compactness, averaged over Garden, Room, Bonsai, Rubble, and Modern Building.

N_{\mathrm{GS}}

is reported in millions. The best results are shown in bold.

I_{\mathrm{gray}}\leftarrow\operatorname{mean}(I,\mathrm{dim}=1,\mathrm{keepdim}=\mathrm{true}),\qquad I_{\mathrm{gray}}\in\mathbb{R}^{B\times 1\times H_{\mathrm{img}}\times W_{\mathrm{img}}}

Appendix

Algorithm 1 Frequency-Aware Mask Generation

Explore similar work

ACE-GS: Acing the Trade-off with Accurate, Compact and Efficient 3D Gaussian Splatting
Jun 19, 2026Jijian Zhao3D Generation Sparsity
Huazhong University of Science and Technology, Wuhan, China
SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training
Mar 9, 2026Jingxing Li, Yongjae Lee, Deliang FanSkip Backward Passes
Arizona State University, Tempe, AZ 85281, USA
BlitzGS: City-Scale Gaussian Splatting at Lightning Speed
May 13, 2026Zhongtao Wang, Huishan Au, Yilong Li +6Gaussian Primitives Speeds
Peking University, China

Jun 19, 2026, cs.CVJ/K move · Enter open · S save

ACE-GS: Acing the Trade-off with Accurate, Compact and Efficient 3D Gaussian Splatting

Jijian Zhao

Huazhong University of Science and Technology, Wuhan, China

3D Generation Sparsity Trade-Off

Open paper AskPDF arXiv

3D Gaussian Splatting achieves exceptional real-time rendering, but its substantial computational and storage demands hinder widespread deployment. Existing accelerated paradigms often aggressively prune primitives for rapid convergence, causing severe loss of high-frequency details. To address this, we tackle the fundamental problem of achieving both exceptional rendering quality and ultra-fast reconstruction speed. In this paper, we propose ACE-GS, a progressive optimization framework tailored for accurate, compressed, and efficient scene representation. We realize that precise primitive management is the key to breaking this trade-off. Therefore, we first design a momentum consistency-guided densification strategy, strictly constraining primitive growth onto authentic geometric manifolds to avoid computational waste while significantly accelerating convergence. Building upon this efficient initialization, we deploy a statistical sensitivity-driven sparsification mechanism to precisely prune redundant primitives, yielding a further compressed footprint. Finally, to thoroughly compensate for the risk of micro-structure loss caused by the aforementioned strict primitive control, we introduce a cross-dimensional residual frequency compensation scheme that explicitly back-injects high-frequency error energy into primitive attributes, perfectly restoring sharp geometric details. Extensive experiments validate our superiority. While maintaining a highly compact scene representation, our system achieves up to 3.7 times training acceleration against the rapid framework Speedy-Splat. Requiring only 3 to 5 minutes to converge, ACE-GS secures the highest structural similarity and achieves a peak PSNR improvement of up to 0.89 dB over the original 3DGS, establishing a new benchmark for ultra-fast and high-fidelity novel view synthesis.

Abstract

Explore similar work

ACE-GS: Acing the Trade-off with Accurate, Compact and Efficient 3D Gaussian Splatting

SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training

BlitzGS: City-Scale Gaussian Splatting at Lightning Speed