GeoGSplat: Geometry-Grounded Non-Pixel-Aligned Gaussian Splatting

arXiv:2610.36760v1 Announce Type: new Abstract: Feed-forward Gaussian Splatting enables efficient novel view synthesis, but pixel-aligned prediction makes the primitive count grow with image resolution and view count, leading to substantial redundancy and increased computational cost. Non-pixel-aligned methods address this limitation by predicting a fixed number of Gaussians. Without explicit ray and depth constraints, these methods yield misplaced Gaussian centers, causing rendering artifacts under large viewpoint changes. To address this issue, we introduce GeoGSplat, a geometry-grounded feed-forward model that explicitly incorporates geometric priors into the non-pixel-aligned framework. A dual-branch encoder constructs Anchors and Triplane to capture coarse 3D structure and fine-grained scene features, respectively. Subsequently, a hierarchical decoder progressively decodes dense 3D points and Gaussian primitives, enabling 3D reconstruction and novel view synthesis. GeoGSplat surpasses both state-of-the-art pixel-aligned and non-pixel-aligned Gaussian Splatting methods on DTU and NRGBD in terms of novel view synthesis and reconstruction. The advantage of our geometry-grounded paradigm further increases as target viewpoints move farther from the input cameras, demonstrating stronger generalization to large viewpoint changes. Project Page: https://comedy0913.github.io/projects/geogsplat

Related

• CoMVS-GS: Collaborative Multi-View Stereo and 3D Gaussian Splatting for Surface Reconstruction
• PointSplat: Efficient Geometry-Driven Pruning and Transformer Refinement for 3D Gaussian Splatting
• ext{VG}^2GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer

Source: arXiv cs.CV | 2026-10-28