HeroGS：面向稀疏视角下鲁棒三维高斯泼溅的层次化引导
HeroGS: Hierarchical Guidance for Robust 3D Gaussian Splatting under Sparse Views
针对稀疏视角下 3DGS 高斯分布退化的问题，提出图像级伪稠密监督、特征级自适应稠密化与剪枝、参数级协同剪枝几何一致性三级引导，可直接迁移到任何稀疏输入的新视角合成或三维重建流程中作为正则化与致密化策略。
原文依据 under sparse-view conditions, insufficient supervision leads to irregular Gaussian distributions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维高斯泼溅（3DGS）近期成为新视角合成中一种有前景的方法，它将照片级真实感渲染与实时效率结合起来。然而，其成功在很大程度上依赖于稠密的相机覆盖；在稀疏视角条件下，监督不足会导致不规则的高斯分布——表现为全局覆盖稀疏、背景模糊以及高频区域失真。为解决这一问题，我们提出 HeroGS——面向鲁棒三维高斯泼溅的层次化引导——一个在图像、特征与参数三个层级上建立层次化引导的统一框架。在图像层级，稀疏监督被转换为伪稠密引导，对高斯分布进行全局正则化，并为后续优化形成一致的基础。在此基础上，特征层级的特征自适应稠密化与剪枝（FADP）利用低层特征细化高频细节，并在背景区域自适应地稠密化高斯。优化后的分布随后支撑参数层级的协同剪枝几何一致性（CPG），它通过参数冻结与协同剪枝来引导几何一致性，有效去除不一致的高斯泼溅。该层次化引导策略有效约束并优化了整体高斯分布，从而同时提升结构保真度与渲染质量。大量实验表明，HeroGS 实现了高保真重建，并在稀疏视角条件下持续超越最优基线。
英文原文摘要 1582 字符
3D Gaussian Splatting (3DGS) has recently emerged as a promising approach in novel view synthesis, combining photorealistic rendering with real-time efficiency. However, its success heavily relies on dense camera coverage; under sparse-view conditions, insufficient supervision leads to irregular Gaussian distributions--characterized by globally sparse coverage, blurred background, and distorted high-frequency areas.To address this, we propose HeroGS--Hierarchical Guidance for Robust 3D Gaussian Splatting--a unified framework that establishes hierarchical guidance across the image, feature, and parameter levels. At the image level, sparse supervision is converted into pseudo-dense guidance, globally regularizing the Gaussian distributions and forming a consistent foundation for subsequent optimization. Building upon this, Feature-Adaptive Densification and Pruning (FADP) at the feature level leverages low-level features to refine high-frequency details and adaptively densifies Gaussians in background regions.The optimized distributions then support Co-Pruned Geometry Consistency (CPG) at parameter level, which guides geometric consistency through parameter freezing and co-pruning, effectively removing inconsistent splats. The hierarchical guidance strategy effectively constrains and optimizes the overall Gaussian distributions, thereby enhancing both structural fidelity and rendering quality.Extensive experiments demonstrate that HeroGS achieves high-fidelity reconstructions and consistently surpasses state-of-the-art baselines under sparse-view conditions.