Unfolding 3D Gaussian Splatting via Iterative Gaussian Synopsis

2026-04-13

AI Summary

This work addresses the challenges of large storage overhead, unstructured representation, and fidelity loss or redundancy in existing level-of-detail (LOD) methods for 3D Gaussian splatting under streaming and resource-constrained scenarios. The authors propose a top-down multi-level LOD construction mechanism that begins with a full-resolution Gaussian model and iteratively prunes Gaussians via learnable masks. By integrating a hierarchical spatial grid with a shared anchor codebook, the method yields a compact and structured Gaussian representation. It introduces an iterative pruning–based Gaussian summarization strategy that enables inter-level feature reuse and supports progressive rendering with minimal data overhead. Experiments demonstrate that the approach maintains high rendering quality across all LOD levels while achieving significant storage compression, making it well-suited for real-time applications with limited bandwidth and memory.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

3D Gaussian Splatting (3DGS) has become a state-of-the-art framework for real-time, high-fidelity novel view synthesis. However, its substantial storage requirements and inherently unstructured representation pose challenges for deployment in streaming and resource-constrained environments. Existing Level-of-Detail (LOD) strategies, particularly those based on bottom-up construction, often introduce redundancy or lead to fidelity degradation. To overcome these limitations, we propose Iterative Gaussian Synopsis, a novel framework for compact and progressive rendering through a top-down "unfolding" scheme. Our approach begins with a full-resolution 3DGS model and iteratively derives coarser LODs using an adaptive, learnable mask-based pruning mechanism. This process constructs a multi-level hierarchy that preserves visual quality while improving efficiency. We integrate hierarchical spatial grids, which capture the global scene structure, with a shared Anchor Codebook that models localized details. This combination produces a compact yet expressive feature representation, designed to minimize redundancy and support efficient, level-specific adaptation. The unfolding mechanism promotes inter-layer reusability and requires only minimal data overhead for progressive refinement. Experiments show that our method maintains high rendering quality across all LODs while achieving substantial storage reduction. These results demonstrate the practicality and scalability of our approach for real-time 3DGS rendering in bandwidth- and memory-constrained scenarios.

Problem

• 3D Gaussian Splatting
• Level-of-Detail
• storage efficiency
• progressive rendering
• resource-constrained deployment

Innovation

• 3D Gaussian Splatting
• Level-of-Detail
• Iterative Gaussian Synopsis
• Progressive Rendering
• Adaptive Pruning