AI Paper Atlas

Research map / 3D vision / Gaussian splatting

UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound Volumes

Mark C. Eid, Ana Namburete, Joao F. Henriques

ICLR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use UltraGauss instead of RapidVolfetal cinesweep reconstruction · held-out test frames (avg of 3 videos)test SSIM: 0.768 -> 0.914Improved
use UltraGauss instead of RapidVolfetal cinesweep reconstruction · training frames (avg)train SSIM: 0.878 -> 0.952Improved
use UltraGauss instead of RapidVol (variability)fetal cinesweep reconstruction · train SSIM std across videosstd: 0.007 -> 0.011Hurt
increase starting gaussians (100K to 2M) (ablation)UltraGauss · 3D ultrasound reconstructionSSIM / clinician preferenceMixed
use fewer gaussians (ablation)UltraGauss · 3D ultrasound reconstructionfinal accuracy and speedMixed
use UltraGauss instead of RapidVol/ImplicitVol at t=5 minUltraGauss · Dataset A reconstructionSSIM: at least 0.2 SSIM higherImproved
replace quaternion-based covariance with triangular parameterizationUltraGauss · covariance parametrizationnumerical stabilityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy