From Scan to Action: Leveraging Realistic Scans for Embodied Scene Understanding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Halacheva, Anna-Maria, Zaech, Jan-Nico, Dey, Sombit, Van Gool, Luc, Paudel, Danda Pani
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911073031946240
author Halacheva, Anna-Maria
Zaech, Jan-Nico
Dey, Sombit
Van Gool, Luc
Paudel, Danda Pani
author_facet Halacheva, Anna-Maria
Zaech, Jan-Nico
Dey, Sombit
Van Gool, Luc
Paudel, Danda Pani
contents Real-world 3D scene-level scans offer realism and can enable better real-world generalizability for downstream applications. However, challenges such as data volume, diverse annotation formats, and tool compatibility limit their use. This paper demonstrates a methodology to effectively leverage these scans and their annotations. We propose a unified annotation integration using USD, with application-specific USD flavors. We identify challenges in utilizing holistic real-world scan datasets and present mitigation strategies. The efficacy of our approach is demonstrated through two downstream applications: LLM-based scene editing, enabling effective LLM understanding and adaptation of the data (80% success), and robotic simulation, achieving an 87% success rate in policy learning.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17585
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Scan to Action: Leveraging Realistic Scans for Embodied Scene Understanding
Halacheva, Anna-Maria
Zaech, Jan-Nico
Dey, Sombit
Van Gool, Luc
Paudel, Danda Pani
Computer Vision and Pattern Recognition
Robotics
Real-world 3D scene-level scans offer realism and can enable better real-world generalizability for downstream applications. However, challenges such as data volume, diverse annotation formats, and tool compatibility limit their use. This paper demonstrates a methodology to effectively leverage these scans and their annotations. We propose a unified annotation integration using USD, with application-specific USD flavors. We identify challenges in utilizing holistic real-world scan datasets and present mitigation strategies. The efficacy of our approach is demonstrated through two downstream applications: LLM-based scene editing, enabling effective LLM understanding and adaptation of the data (80% success), and robotic simulation, achieving an 87% success rate in policy learning.
title From Scan to Action: Leveraging Realistic Scans for Embodied Scene Understanding
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2507.17585