titleSplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes
authorsHao Yu, Zhenwei Wang, Yongzhen Hu, Yuning Gong, Junta Wu, Xiaowei Zhou, Hujun Bao, Tengfei Wang, Chunchao Guo, Sida Peng
date2026-11-05
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.08264
affiliationZhejiang University
upvotes69 (Hugging Face Daily Papers, 2026-11-11)
linksabs pdf hf code
cite
relatednanoMuse: An Open-Source Personal Agent for Every Device You Own
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
abstractWe 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.

bibtex

@misc{yu2026splatanything,
  title={SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes},
  author={Hao Yu and Zhenwei Wang and Yongzhen Hu and Yuning Gong and Junta Wu and Xiaowei Zhou and Hujun Bao and Tengfei Wang and Chunchao Guo and Sida Peng},
  year={2026},
  eprint={2611.08264},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.08264}
}