UltraGS: Real-Time Physically-Decoupled Gaussian Splatting for Ultrasound Novel View Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914514119688192 |
|---|---|
| author | Yang, Yuezhe Ruan, Qingqing Cai, Wenjie Dong, Yudang Yang, Dexin Dong, Xingbo Jin, Zhe Dai, Yong |
| author_facet | Yang, Yuezhe Ruan, Qingqing Cai, Wenjie Dong, Yudang Yang, Dexin Dong, Xingbo Jin, Zhe Dai, Yong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07743 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UltraGS: Real-Time Physically-Decoupled Gaussian Splatting for Ultrasound Novel View Synthesis Yang, Yuezhe Ruan, Qingqing Cai, Wenjie Dong, Yudang Yang, Dexin Dong, Xingbo Jin, Zhe Dai, Yong Computer Vision and Pattern Recognition Artificial Intelligence I.4.5 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. |
| title | UltraGS: Real-Time Physically-Decoupled Gaussian Splatting for Ultrasound Novel View Synthesis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence I.4.5 |
| url | https://arxiv.org/abs/2511.07743 |