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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dokania, Srijan, Raghavan, Dharini
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911309520437248
author Dokania, Srijan
Raghavan, Dharini
author_facet Dokania, Srijan
Raghavan, Dharini
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08271
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zero-Splat TeleAssist: A Zero-Shot Pose Estimation Framework for Semantic Teleoperation
Dokania, Srijan
Raghavan, Dharini
Robotics
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
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.
title Zero-Splat TeleAssist: A Zero-Shot Pose Estimation Framework for Semantic Teleoperation
topic Robotics
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2512.08271