Metraipolis › archive › dc_71dfaaced828
SurgGMF: Fully Causal Gaussian Motion Forecasting for Anticipatory Surgical Scene Rendering — arXiv:2609.34733
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34733
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:52:24.471Z
- SHA-256 of the archived text
55bff6a76c67ec9cb021df3d21624e12c9759f441cba6578df01b44302adfcca- Stable URL of this page
https://metraipolis.com/documento/dc_71dfaaced828
How to cite
SurgGMF: Fully Causal Gaussian Motion Forecasting for Anticipatory Surgical Scene Rendering — arXiv:2609.34733 — arXiv (en), https://arxiv.org/abs/2609.34733 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_71dfaaced828 (Metraipolis archive dc_71dfaaced828, sha256 55bff6a76c67ec9cb021df3d21624e12c9759f441cba6578df01b44302adfcca)
BibTeX
@misc{dc71dfaaced828,
title = {SurgGMF: Fully Causal Gaussian Motion Forecasting for Anticipatory Surgical Scene Rendering — arXiv:2609.34733},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34733},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_71dfaaced828; sha256 55bff6a76c67ec9cb021df3d21624e12c9759f441cba6578df01b44302adfcca},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34733. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dynamic surgical scene modeling is essential for robotic perception, simulation, and decision support. Although existing neural rendering methods enable efficient reconstruction and rendering of deformable surgical scenes, they remain primarily focused on observed-frame reconstruction rather than forecasting future scene states. To this end, we present SurgGMF, a fully causal Gaussian motion forecasting framework for anticipatory surgical scene rendering. Rather than predicting future RGB images directly, SurgGMF forecasts future Gaussian motion states represented by position, scale, and rotation residuals (X/S/R) from historical Gaussian motion fields. To prevent target leakage, we introduce a full-causal-last rendering protocol, where future Gaussian states are rendered without accessing target-frame Gaussian attributes while preserving causal appearance propagation. We evaluate SurgGMF on 12 EndoNeRF and StereoMIS video slices using neural temporal learners and classical dynamics baselines under a unified forecasting protocol. Learned Gaussian motion forecasting consistently outperforms classical dynamics baselines in render space, demonstrating gains beyond hand-crafted state extrapolation. Latency analysis further reveals an accuracy--efficiency trade-off: under the current implementations, TKAN achieves the highest accuracy, whereas GRU and LSTM provide more favorable module-level latency profiles. These results establish SurgGMF as a reproducible framework for causal Gaussian motion forecasting and advance surgical Gaussian representations from retrospective reconstruction toward predictive scene modeling. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.34733 — 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 2026-10-07T23:29:27.445Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).