实时生成超声新视角，兼顾精度与速度
UltraGS: Real-Time Physically-Decoupled Gaussian Splatting for Ultrasound Novel View Synthesis
- 用可学习视场的高斯点建模，适应探头任意移动
- 实测达到29.55分的PSNR和64.69帧/秒速度
- 专为临床超声设计，适合医学影像生成研究者
超声成像在无创临床诊断中至关重要，但视野受限导致新视角合成困难。我们提出UltraGS，一种实时框架，通过将显式辐射场与轻量级物理启发声学建模结合，适配无传感器超声成像。UltraGS采用深度感知的高斯原语及可学习视场，提升探头自由运动下的几何一致性；引入可微分的PD渲染机制，融合低阶球谐函数与一阶波效应，高效合成强度图像。我们还构建了一个基于真实扫描协议的临床超声数据集。在三个数据集上的大量评估表明，UltraGS在性能与效率上树立新标杆，达到最高29.55的PSNR和0.89的SSIM，单张GPU实现64.69帧/秒的实时合成。代码与数据集已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。