GaussianFocus: Constrained Attention Focus for 3D Gaussian Splatting

2025-03-22

AI Summary

To address excessive Gaussian redundancy, overfitting to training views, and limited memory efficiency and optimization scalability in large-scale 3D Gaussian Splatting, this paper introduces a focus-aware attention mechanism and explicit redundancy suppression, embedded within an extensible block-wise collaborative optimization framework. Key contributions include: (1) the first patch-level constrained attention mechanism enabling joint local geometry-appearance weighted rendering; (2) explicit Gaussian redundancy suppression via distribution-aware pruning; and (3) adaptive spatial tiling with cross-tile consistency regularization. Experiments demonstrate a 38% average reduction in redundant Gaussians and superior PSNR/SSIM over state-of-the-art methods. Notably, our approach achieves the first high-fidelity, real-time renderable 3D reconstruction at urban scale (>1 km²), significantly advancing scalability and visual quality for large-scene Gaussian splatting.

Technology Category

• Computer Vision: 3D Computer Vision
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Recent developments in 3D reconstruction and neural rendering have significantly propelled the capabilities of photo-realistic 3D scene rendering across various academic and industrial fields. The 3D Gaussian Splatting technique, alongside its derivatives, integrates the advantages of primitive-based and volumetric representations to deliver top-tier rendering quality and efficiency. Despite these advancements, the method tends to generate excessive redundant noisy Gaussians overfitted to every training view, which degrades the rendering quality. Additionally, while 3D Gaussian Splatting excels in small-scale and object-centric scenes, its application to larger scenes is hindered by constraints such as limited video memory, excessive optimization duration, and variable appearance across views. To address these challenges, we introduce GaussianFocus, an innovative approach that incorporates a patch attention algorithm to refine rendering quality and implements a Gaussian constraints strategy to minimize redundancy. Moreover, we propose a subdivision reconstruction strategy for large-scale scenes, dividing them into smaller, manageable blocks for individual training. Our results indicate that GaussianFocus significantly reduces unnecessary Gaussians and enhances rendering quality, surpassing existing State-of-The-Art (SoTA) methods. Furthermore, we demonstrate the capability of our approach to effectively manage and render large scenes, such as urban environments, whilst maintaining high fidelity in the visual output.

Problem

• Reduces redundant noisy Gaussians in 3D rendering
• Improves rendering quality with patch attention algorithm
• Enables large-scale scene handling via subdivision strategy

Innovation

• Patch attention algorithm improves rendering quality
• Gaussian constraints strategy reduces redundancy
• Subdivision reconstruction handles large-scale scenes