# Zero-Splat TeleAssist: A Zero-Shot Pose Estimation Framework for Semantic Teleoperation

arXiv: https://arxiv.org/abs/2512.08271 · HTML: https://mlsanity.com/paper/2512.08271/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 3 of its 6 references that are in the map.
- First posted on arXiv 9 Dec 2025.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 3 of 3)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Markerless Camera-to-Robot Pose Estimation via Self-supervised Sim-to-Real Transfer](https://mlsanity.com/paper/2302.14332/) (2023)

## Built on by (most cited first, 1 of 1)

- [Do Better Imagined Rollouts Mean Better Robot Control? A Controlled Study of World-Model Evaluation Under Feedback](https://mlsanity.com/paper/2609.02811/) (2026)

## Abstract (arXiv)

We introduce Zero-Splat TeleAssist, a zero-shot sensor-fusion pipeline that transforms commodity CCTV streams into a shared, 6-DoF world model for multilateral teleoperation. By integrating vision-language segmentation, monocular depth, weighted-PCA pose extraction, and 3D Gaussian Splatting (3DGS), TeleAssist provides every operator with real-time global positions and orientations of multiple robots without fiducials or depth sensors in an interaction-centric teleoperation setup.