SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes

Hao Yu; Zhenwei Wang; Yongzhen Hu; Yuning Gong; Junta Wu; Xiaowei Zhou; Hujun Bao; Tengfei Wang

cs.CVNov 5, 2026

SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes

Authors: Hao Yu, Zhenwei Wang, Yongzhen Hu, Yuning Gong, Junta Wu, Xiaowei Zhou, Hujun Bao, Tengfei Wang,

Organizations: Zhejiang University · Tencent Hunyuan · Causa Robotics

Abstract

We identify a key limitation of existing feed-forward 3DGS methods: Gaussian attributes are typically predicted in a radial-distance-normalized space that canonicalizes a global radial statistic of the reconstructed geometry, while the spacing between neighboring Gaussian centers can still vary substantially across scene scales and camera configurations. This mismatch induces systematic shifts in Gaussian-scale targets, leading to ambiguous supervision. To address this, we propose SplatAnything with Gaussian Spacing Normalization (GSNorm), which canonicalizes a robust scene-level statistic of Gaussian spacing to provide a more consistent spatial reference for Gaussian prediction. To rigorously assess our method, we further establish a systematic benchmark spanning diverse datasets, input sparsity levels, and challenging extrapolated viewpoints. Extensive experiments demonstrate that SplatAnything achieves state-of-the-art performance, with particularly strong gains under substantial variations in scene scale and viewpoint.

Figures & tables

Figure 1: Given any number of input images and optional camera poses, SplatAnything reconstructs a 3D Gaussian Splatting (3DGS) representation within seconds. It generalizes across arbitrary scene scales and camera configurations, while supporting challenging extrapolated viewpoints. Compared with prior feed-forward 3DGS methods, SplatAnything achieves substantially stronger cross-scene generalization and novel-view rendering quality.

Figure 2: Normalization space. (a) Radial Distance Normalization canonicalizes a global radial statistic but leaves Gaussian spacing varying across scenes and camera configurations, resulting in inconsistent supervision targets. (b) Gaussian Spacing Normalization canonicalizes a representative statistic of Gaussian spacing, providing a more consistent spatial reference for Gaussian prediction.

Figure 3: Architecture of SplatAnything. Given $N$ input images and optional camera parameters, a frozen geometry foundation model first estimates multi-view geometry. We convert the geometry from its native radial-distance-normalized space to the proposed Gaussian-spacing-normalized space and predict per-pixel Gaussian attribute through a Gaussian backbone and a lightweight GShead.

Figure 4: Median Gaussian spacing across scene types. RDNorm leaves up to

4.5\times

variation in median Gaussian spacing across scene categories, whereas GSNorm canonicalizes it by construction.

Figure 5: Qualitative comparisons across diverse scenes and viewpoints with multi-view input.

Table 2: Quantitative comparison of feed-forward 3DGS methods using a single input view . The top-3 results are highlighted as first , second , and third .

Figure 7: Ablation studies on the effect of GSNorm across different scene types.

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Data Type	Dataset	# Scenes	Resolution ( $H\times W$ )
Synthetic	HyperSim ( Roberts et al., 2021 )	364	768 $\times$ 1024
	UnrealStereo4K ( Tosi et al., 2021 )	18	1080 $\times$ 1920
	OmniObject3D ( Wu et al., 2023 )	5914	800 $\times$ 800
	Rawmantic3D ( Team, 2026 )	30	1080 $\times$ 1920
	OmniWorld ( Zhou et al., 2025 )	10464	720 $\times$ 1280
	GTA-SfM ( Wang and Shen, 2020 )	200	480 $\times$ 640

Appendix

Table 4: Details of the training datasets used by SplatAnything.

Figure 8: Source-view trajectory patterns ( $16$ views per panel), visualized in an approximately top-down projection. Dots and arrows denote camera centers and viewing directions, respectively; the gray polyline connects consecutive views, and color indicates capture order. For inward-orbit , $\times$ marks the approximate viewing center.

Figure 9: Target-view sampling modes used during training. Blue cameras denote the source views provided as input, while red cameras denote the target views used for rendering supervision.

Input	Method	4 Views	8 Views	16 Views	32 Views	64 Views
Input	Method	PSNR $\uparrow$	PSNR $\uparrow$	PSNR $\uparrow$	PSNR $\uparrow$	PSNR $\uparrow$
w/o Pose	AnySplat	12.68	13.20	12.83	13.12	14.26
	YoNoSplat	18.23	18.64	18.73	18.34	15.79
	DA3-GS	16.32	16.94	16.73	17.17	17.26
	Mirror2-GS	17.20	17.60	17.98	17.04	17.09
	QuerySplat	17.77	18.26	18.33	17.84	16.90

Appendix

Table 8: Quantitative comparison across seven benchmark datasets using 32 input views . The top-3 results are highlighted as first , second , and third .

Input	Method	$N=4$	$N=8$	$N=16$	$N=32$	$N=64$
w/o Pose	AnySplat	250	487	1,089	2,743	7,798
	DA3-GS	709	1,513	3,783	10,950	35,904
	Mirror2-GS	246	448	959	2,268	6,060
	QuerySplat	2,324	3,398	6,092	14,009	39,583
	Ours	411	761	1,649	3,991	11,037
w/ Pose	DepthSplat	158	287	541	1,045	2,087

Appendix

Table 11: Median forward-pass latency per scene (ms) of different methods under different numbers of input views. The fastest method within each pose setting is highlighted in bold.

Panel of Table 12 — Table 12: Ablation study of different normalization spaces across different numbers of input views.

Figure 11: Qualitative comparisons across diverse scenes and viewpoints with multi-view input.

Figure 12: Qualitative comparisons across diverse scenes and viewpoints with monocular input.

Figure 13: Qualitative results of SplatAnything for panoramic images reconstruction. SplatAnything can reconstruct high-quality 3DGS representations from panoramic images with different field of view, demonstrating its strong generalization ability.

Figure 14: More qualitative results of our method. SplatAnything feed-forward reconstructs high-quality 3DGS representations generalizing to arbitrary scenes, scales, and viewpoints in a few seconds.

3D Gaussian Splatting

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

See all 1,051 papers

SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction
Apr 3, 2026Zicheng Zhang, Xiangting Meng, Ke Wu +13D Gaussian Splatting Feed-Forward 3D Reconstruction
Fudan University · ShanghaiTech University
TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
Apr 16, 2026Jiawei Ren, Michal Jan Tyszkiewicz, Jiahui Huang +13D Gaussian Splatting 3D ViTs
NVIDIA
AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors
Apr 8, 2026Xiaoxue Zhang, Xiaoxu Zheng, Yixuan Yin +53D Gaussian Splatting 3D Reconstruction

Apr 3, 2026J/K move · Enter open · S save

SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction

Zicheng Zhang, Xiangting Meng, Ke Wu, Wenchao Ding

Fudan University · ShanghaiTech University

3D Gaussian Splatting Feed-Forward 3D Reconstruction Adaptive Gaussian Densification

Open paper AskPDF arXiv

Recent progress in feed-forward 3D Gaussian Splatting (3DGS) has notably improved rendering quality. However, the spatially uniform and highly redundant 3DGS map generated by previous feed-forward 3DGS methods limits their integration into downstream reconstruction tasks. We propose SparseSplat, the first feed-forward 3DGS model that adaptively adjusts Gaussian density according to scene structure and information richness of local regions, yielding highly compact 3DGS maps. To achieve this, we propose entropy-based probabilistic sampling, generating large, sparse Gaussians in textureless areas and assigning small, dense Gaussians to regions with rich information. Additionally, we designed a specialized point cloud network that efficiently encodes local context and decodes it into 3DGS attributes, addressing the receptive field mismatch between the general 3DGS optimization pipeline and feed-forward models. Extensive experimental results demonstrate that SparseSplat can achieve state-of-the-art rendering quality with only 22% of the Gaussians and maintain reasonable rendering quality with only 1.5% of the Gaussians. Project page: https://victkk.github.io/SparseSplat-page/.

Abstract

3D Gaussian Splatting

Explore similar work

SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction

TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens

AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors