SplatCo通过结构与视角协同优化，实现大规模无界场景的高保真渲染。
SplatCo: Structure-View Collaborative Gaussian Splatting for Detail-Preserving Rendering of Large-Scale Unbounded Scenes
- 融合全局三平面与局部上下文网格，分层补偿以兼顾整体布局与细节。
- 基于结构一致性剪枝冗余高斯点，提升存储效率并避免渲染伪影。
- 结构梯度与视角梯度联合学习，更稳健地优化高斯点几何与外观属性。
我们提出SplatCo，一种用于复杂室外场景高保真渲染的结构-视角协同高斯点渲染框架。SplatCo包含三个新组件：1）跨结构协作模块，将捕捉粗略场景布局的全局三平面表示与表征精细细节的局部上下文网格特征相结合，通过分层补偿机制实现融合，兼顾全局空间感知与局部细节保留；2）跨视角剪枝机制，基于结构一致性剔除过拟合或不准确的高斯点，提升存储效率并防止渲染伪影；3）结构-视角协同学习模块，聚合结构梯度与视角梯度，更稳健地引导高斯点几何与外观属性的优化。结合这些关键组件，SplatCo有效实现了对大规模场景的高保真渲染。代码与项目页面见https://splatco-tech.github.io。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。