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, Chunchao Guo, Sida Peng

SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes: 69 upvotes on Hugging Face Daily Papers, #2 of 34 papers on 2026-11-09. Day-by-day upvote history.

Upvotes over time

It had 60 upvotes by its first day, 68 upvotes by the next day, 69 upvotes by day 3, 69 upvotes by day 7, and has 69 now. It ranked #4 of 133 papers in its week and #16 of 340 in its month. Its code repository has 205 GitHub stars.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.