Duplex-GS: Proxy-Guided Weighted Blending for Real-Time Order-Independent Gaussian Splatting

TL;DR

Duplex-GS introduces a proxy-guided, order-independent Gaussian Splatting framework that significantly improves real-time rendering efficiency and quality by reducing computational overhead and artifacts in 3D Gaussian rendering.

Contribution

The paper presents a novel dual-hierarchy framework with proxy representations and cell search rasterization, enabling real-time, high-quality Gaussian Splatting with reduced sorting overhead and artifact elimination.

Findings

Achieves 1.5 to 4 times speedup over existing methods.

Reduces radix sort overhead by up to 86.9%.

Maintains high rendering quality across diverse datasets.

Abstract

Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated remarkable rendering fidelity and efficiency. However, these methods still rely on computationally expensive sequential alpha-blending operations, resulting in significant overhead, particularly on resource-constrained platforms. In this paper, we propose Duplex-GS, a dual-hierarchy framework that integrates proxy Gaussian representations with order-independent rendering techniques to achieve photorealistic results while sustaining real-time performance. To mitigate the overhead caused by view-adaptive radix sort, we introduce cell proxies for local Gaussians management and propose cell search rasterization for further acceleration. By seamlessly combining our framework with Order-Independent Transparency (OIT), we develop a physically inspired weighted sum rendering technique that simultaneously eliminates "popping" and "transparency" artifacts, yielding substantial improvements in both accuracy and efficiency. Extensive experiments on a variety of real-world datasets demonstrate the robustness of our method across diverse scenarios, including multi-scale training views and large-scale environments. Our results validate the advantages of the OIT rendering paradigm in Gaussian Splatting, achieving high-quality rendering with an impressive 1.5 to 4 speedup over existing OIT based Gaussian Splatting approaches and 52.2% to 86.9% reduction of the radix sort overhead without quality degradation.