UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound Volumes

Abstract

Ultrasound imaging is widely used due to its safety, affordability, and real-time capabilities, but its 2D interpretation is highly operator-dependent, leading to variability and increased cognitive demand. We present $\textbf{UltraGauss}$: an ultrasound-specific Gaussian Splatting framework that serves as an efficient approximation to acoustic image formation. Unlike projection-based splatting, UltraGauss renders by $\textit{probe-plane intersection}$ with in-plane aggregation, aligning with plane-based echo sampling while remaining fast and memory-efficient. A stable parameterisation and compute-aware GPU rasterisation make this method practical at scale. On clinical datasets, UltraGauss delivers state-of-the-art 2D-to-3D reconstructions in minutes on a single GPU (reaching 0.99 SSIM within $\sim$20 minutes), and a clinical expert survey rates its reconstructions the most realistic among competing methods. To our knowledge, this is the first Gaussian Splatting approach tailored to ultrasound 2D-to-3D reconstruction. Our code is available at: https://www.robots.ox.ac.uk/~vgg/research/UltraGauss/

Cite

Text

Eid et al. "UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound Volumes." International Conference on Learning Representations, 2026.

Markdown

[Eid et al. "UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound Volumes." International Conference on Learning Representations, 2026.](https://mlanthology.org/iclr/2026/eid2026iclr-ultragauss/)

BibTeX

@inproceedings{eid2026iclr-ultragauss,
  title     = {{UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound Volumes}},
  author    = {Eid, Mark C. and Namburete, Ana and Henriques, Joao F.},
  booktitle = {International Conference on Learning Representations},
  year      = {2026},
  url       = {https://mlanthology.org/iclr/2026/eid2026iclr-ultragauss/}
}