UltraGS: Gaussian Splatting for Ultrasound Novel View Synthesis
This addresses the limited field of view in ultrasound diagnostics, offering a domain-specific incremental improvement for clinical applications.
The paper tackles novel view synthesis in ultrasound imaging by proposing UltraGS, a Gaussian Splatting framework optimized for this domain, achieving state-of-the-art results with PSNR up to 29.55, SSIM up to 0.89, and real-time synthesis at 64.69 fps.
Ultrasound imaging is a cornerstone of non-invasive clinical diagnostics, yet its limited field of view complicates novel view synthesis. We propose \textbf{UltraGS}, a Gaussian Splatting framework optimized for ultrasound imaging. First, we introduce a depth-aware Gaussian splatting strategy, where each Gaussian is assigned a learnable field of view, enabling accurate depth prediction and precise structural representation. Second, we design SH-DARS, a lightweight rendering function combining low-order spherical harmonics with ultrasound-specific wave physics, including depth attenuation, reflection, and scattering, to model tissue intensity accurately. Third, we contribute the Clinical Ultrasound Examination Dataset, a benchmark capturing diverse anatomical scans under real-world clinical protocols. Extensive experiments on three datasets demonstrate UltraGS's superiority, achieving state-of-the-art results in PSNR (up to 29.55), SSIM (up to 0.89), and MSE (as low as 0.002) while enabling real-time synthesis at 64.69 fps. The code and dataset are open-sourced at: https://github.com/Bean-Young/UltraGS.