GeoGSplat grounds non-pixel-aligned feed-forward Gaussians with geometric priors

arXivarXivPapers

GeoGSplat grounds non-pixel-aligned feed-forward Gaussians with geometric priors
arXiv / Jiale Wang, Chen Zhao and colleagues

Jiale Wang, Chen Zhao, Haoyang Zhang and colleagues present GeoGSplat, a geometry-grounded feed-forward model that predicts a fixed number of Gaussians rather than one per pixel. They argue that without explicit ray and depth constraints, non-pixel-aligned methods misplace Gaussian centres and produce artifacts under large viewpoint changes.

A dual-branch encoder constructs Anchors and a Triplane to capture coarse 3D structure and fine scene features, and a hierarchical decoder progressively decodes dense 3D points and Gaussian primitives. On DTU and NRGBD, GeoGSplat surpasses both pixel-aligned and non-pixel-aligned Gaussian Splatting methods in novel-view synthesis and reconstruction, with a larger advantage as target viewpoints move farther from the input cameras.