HeroGS: Hierarchical Guidance for Robust 3D Gaussian Splatting under Sparse Views
This addresses a critical bottleneck in 3D reconstruction for applications like VR/AR by making 3D Gaussian Splatting robust to sparse inputs, though it is an incremental improvement over existing methods.
The paper tackles the problem of 3D Gaussian Splatting failing under sparse camera views by proposing HeroGS, a hierarchical guidance framework that improves structural fidelity and rendering quality, achieving high-fidelity reconstructions and outperforming state-of-the-art baselines in sparse-view conditions.
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.