HeroGS: Hierarchical Guidance for Robust 3D Gaussian Splatting under Sparse Views

2026-03-01

AI Summary

This work addresses the challenge of irregular Gaussian distributions in 3D Gaussian Splatting under sparse-view settings, which often leads to background blurriness and distortion of high-frequency details due to insufficient supervision. To mitigate this, the authors propose HeroGS, a novel framework featuring a three-level collaborative guidance mechanism—image, feature, and parameter. It introduces pseudo-dense image supervision for global regularization, employs Feature-Adaptive Densification and Pruning (FADP) to enhance local detail recovery, and enforces structural integrity through Co-Pruned Geometric Consistency (CPG) constraints. The proposed method significantly improves reconstruction robustness in sparse-view scenarios, outperforming state-of-the-art approaches in both rendering quality and geometric fidelity.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

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.

Problem

• 3D Gaussian Splatting
• sparse views
• irregular Gaussian distributions
• novel view synthesis
• geometric consistency

Innovation

• Hierarchical Guidance
• 3D Gaussian Splatting
• Sparse Views
• Feature-Adaptive Densification
• Geometry Consistency