SplatCo: Structure-View Collaborative Gaussian Splatting for Detail-Preserving Rendering of Large-Scale Unbounded Scenes

TL;DR

SplatCo introduces a novel Gaussian splatting framework that combines global and local scene features, prunes inaccuracies, and co-learns structural information to enable detailed, high-fidelity rendering of large outdoor scenes.

Contribution

The paper proposes three innovative modules for Gaussian splatting: cross-structure collaboration, cross-view pruning, and structure view co-learning, enhancing detail preservation and efficiency.

Findings

Improved rendering quality for large-scale outdoor scenes.

Enhanced storage efficiency through pruning inaccurate Gaussians.

Robust optimization of Gaussian attributes via structural and view gradient integration.

Abstract

We present SplatCo, a structure-view collaborative Gaussian splatting framework for high-fidelity rendering of complex outdoor scenes. SplatCo builds upon three novel components: 1) a cross-structure collaboration module that combines global tri-plane representations, which capture coarse scene layouts, with local context grid features representing fine details. This fusion is achieved through a hierarchical compensation mechanism, ensuring both global spatial awareness and local detail preservation; 2) a cross-view pruning mechanism that removes overfitted or inaccurate Gaussians based on structural consistency, thereby improving storage efficiency and preventing rendering artifacts; 3) a structure view co-learning module that aggregates structural gradients with view gradients,thereby steering the optimization of Gaussian geometric and appearance attributes more robustly. By combining these key components, SplatCo effectively achieves high-fidelity rendering for large-scale scenes. Code and project page are available at https://splatco-tech.github.io.