# 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, Chunchao Guo, Sida Peng  
**Lab:** Zhejiang University · **Published:** 5 Nov 2026 · **Upvotes:** 60 · **Level:** Intermediate  
**Links:** [arXiv](https://arxiv.org/abs/2611.08264) · [PDF](https://arxiv.org/pdf/2611.08264) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.08264.html)

## Curator's notes

**TL;DR:** SplatAnything normalizes Gaussian spacing for feed-forward 3DGS, improving consistency across varied scenes and viewpoints.

- **What's new:** Introduces Gaussian Spacing Normalization (GSNorm) to canonicalize scene-level spacing statistics, unlike prior methods that only normalize radial distance.
- **Key result:** SplatAnything achieves state-of-the-art performance, especially under large scene-scale and viewpoint variations.
- **Why it matters:** Consistent Gaussian predictions enable more reliable 3D reconstruction across diverse scenes and camera setups.

## 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.

## What you could build

1. Create a real-time 3D scene viewer that adapts to arbitrary camera positions using SplatAnything.
2. Develop a tool to convert sparse point clouds into dense Gaussian splats for VR environments.
3. Implement a benchmark suite to compare 3DGS methods on varying scene scales and viewpoints.

## Quiz yourself

What statistic does GSNorm canonicalize to improve Gaussian prediction consistency?

**Answer:** GSNorm canonicalizes a robust scene-level statistic of Gaussian spacing, providing a consistent spatial reference.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.