SplatAnything normalizes Gaussian spacing for feed-forward 3DGS

arXivarXivPapers

SplatAnything normalizes Gaussian spacing for feed-forward 3DGS
arXiv / Yu et al.

Hao Yu et al. present SplatAnything, a feed-forward 3D Gaussian Splatting method that addresses a mismatch they identify in existing pipelines: attributes are often predicted in a space normalized by a global radial statistic, while the spacing between neighboring Gaussian centers can still vary widely across scene scales and camera setups. That shift, they argue, makes Gaussian-scale supervision ambiguous.

Gaussian Spacing Normalization (GSNorm) canonicalizes a robust scene-level spacing statistic as a more consistent spatial reference. The authors also introduce a benchmark covering diverse datasets, input sparsity and extrapolated viewpoints, and report state-of-the-art results with the largest gains when scene scale and viewpoint vary substantially.