A 129FPS Full HD Real-Time Accelerator for 3D Gaussian Splatting

TL;DR

This paper introduces a specialized hardware accelerator for 3D Gaussian Splatting that achieves real-time 1080p rendering at 129 FPS with significantly improved efficiency and reduced size.

Contribution

It presents a low-power, low-cost hardware design with a novel compression pipeline and optimized processing pipeline for real-time 3D scene rendering.

Findings

Achieves 129 FPS at 1080p resolution.

Reduces model size by 51.6 times with minimal PSNR loss.

Outperforms prior accelerators in size, throughput, and energy efficiency.

Abstract

Rendering large-scale, unbounded scenes on AR/VR-class devices is constrained by the computation, bandwidth, and storage cost of 3D Gaussian Splatting (3DGS). We propose a low-power, low-cost 3DGS hardware accelerator that renders full-HD images in real time, together with a hardware-friendly compression pipeline that combines iterative Gaussian pruning and fine-tuning, progressive spherical harmonics (SH) degree reduction, and vector quantization of all SH coefficients and colors. The scheme achieves a $51.6\times$ model-size reduction with a 0.743 dB PSNR loss. The accelerator uses a frame-level pipeline that integrates point-based culling and projection with tile-based sorting and rasterization, skips zero-Jacobian matrix multiplications (reducing processing elements by 63\% and computation by 53\%), and adopts comparison-free tile-based sorting with deterministic latency. Implemented in a TSMC 28-nm process at 800 MHz, the design occupies $0.66~\text{mm}^2$ with 1.1438 M gates and 120 kB SRAM, consumes 0.219 W, and delivers 1219 Mpixels/J at 267.5 Mpixels/s, enabling 1080p at 129 FPS. Overall, it is $5.98\times$ smaller in area, $5.94\times$ higher throughput, and delivers $7.5\times$ higher energy efficiency than prior 3DGS accelerators.