UltraGS: Real-Time Physically-Decoupled Gaussian Splatting for Ultrasound Novel View Synthesis

TL;DR

UltraGS is a real-time ultrasound view synthesis framework that combines Gaussian splatting with physics-inspired acoustic modeling, achieving high-quality results efficiently.

Contribution

It introduces a novel Gaussian splatting method with physics-based acoustic modeling for real-time ultrasound view synthesis, along with a new clinical dataset.

Findings

Achieves state-of-the-art PSNR of up to 29.55

Real-time synthesis at 64.69 fps on a single GPU

Demonstrates improved geometric consistency under probe motion

Abstract

Ultrasound imaging is a cornerstone of non-invasive clinical diagnostics, yet its limited field of view poses challenges for novel view synthesis. We present UltraGS, a real-time framework that adapts Gaussian Splatting to sensorless ultrasound imaging by integrating explicit radiance fields with lightweight, physics-inspired acoustic modeling. UltraGS employs depth-aware Gaussian primitives with learnable fields of view to improve geometric consistency under unconstrained probe motion, and introduces PD Rendering, a differentiable acoustic operator that combines low-order spherical harmonics with first-order wave effects for efficient intensity synthesis. We further present a clinical ultrasound dataset acquired under real-world scanning protocols. Extensive evaluations across three datasets demonstrate that UltraGS establishes a new performance-efficiency frontier, achieving state-of-the-art results in PSNR (up to 29.55) and SSIM (up to 0.89) while achieving real-time synthesis at 64.69 fps on a single GPU. The code and dataset are open-sourced at: https://github.com/Bean-Young/UltraGS.