Metraipolis › archive › dc_dd18bda935ba
SonoWorld: Towards Interactive Pose-Controllable Ultrasound World Models — arXiv:2610.19327
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19327
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T21:55:53.224Z
- SHA-256 of the archived text
3a198004c8a80282c1c455627d6cb9a29e501e62139d942ff64c96be2f56e81a- Stable URL of this page
https://metraipolis.com/documento/dc_dd18bda935ba
How to cite
SonoWorld: Towards Interactive Pose-Controllable Ultrasound World Models — arXiv:2610.19327 — arXiv (en), https://arxiv.org/abs/2610.19327 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd18bda935ba (Metraipolis archive dc_dd18bda935ba, sha256 3a198004c8a80282c1c455627d6cb9a29e501e62139d942ff64c96be2f56e81a)
BibTeX
@misc{dcdd18bda935ba,
title = {SonoWorld: Towards Interactive Pose-Controllable Ultrasound World Models — arXiv:2610.19327},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19327},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd18bda935ba; sha256 3a198004c8a80282c1c455627d6cb9a29e501e62139d942ff64c96be2f56e81a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19327. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Robotic ultrasound can standardize image acquisition and reduce operator workload and variability, but policy learning remains limited by the lack of realistic, controllable simulation environments. While controllable world models have advanced rapidly in natural-image domains, ultrasound world modeling remains challenging because each frame captures only a cross-section of unobserved 3D anatomy, causing small probe motions to induce large appearance changes. Existing approaches rely on robot-tracked poses and latent-space prediction, but do not directly generate the observations required for interactive control. We propose SonoWorld, a causal ultrasound world model that learns video dynamics from unlabeled clinical videos and grounds them to 6-DoF control using a small set of freehand clinical scans tracked with an EM sensor. SonoWorld is trained in three stages: pretraining a latent-action-conditioned video diffusion model on around 6.9 million unlabeled multi-organ ultrasound frames; grounding the learned video dynamics to metric probe poses with a small EM-tracked thyroid dataset; and applying distribution matching distillation to enable causal, long-horizon autoregressive generation with selectively caching eviction tokens at inference time. We evaluate controllability through pose-following fidelity, round-trip consistency, and axis-specific control under synthetic actions on held-out tracked scans, and further validate it with a user study. In model-based action discrimination, SonoWorld correctly ranks the target-directed probe motion over an equal-magnitude opposite motion in up to 74.8% of trials. To our knowledge, SonoWorld is the first causal, pose-controllable ultrasound world model learned primarily from freehand clinical videos, providing a data-driven interactive environment for robotic ultrasound data acquisition and policy evaluation. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.19327 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T21:38:29.455Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).