ScanEdit: Hierarchically-Guided Functional 3D Scan Editing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916699527184384 |
|---|---|
| author | Boudjoghra, Mohamed el amine Laptev, Ivan Dai, Angela |
| author_facet | Boudjoghra, Mohamed el amine Laptev, Ivan Dai, Angela |
| contents | With the fast pace of 3D capture technology and resulting abundance of 3D data, effective 3D scene editing becomes essential for a variety of graphics applications. In this work we present ScanEdit, an instruction-driven method for functional editing of complex, real-world 3D scans. To model large and interdependent sets of ob- jectswe propose a hierarchically-guided approach. Given a 3D scan decomposed into its object instances, we first construct a hierarchical scene graph representation to enable effective, tractable editing. We then leverage reason- ing capabilities of Large Language Models (LLMs) and translate high-level language instructions into actionable commands applied hierarchically to the scene graph. Fi- nally, ScanEdit integrates LLM-based guidance with ex- plicit physical constraints and generates realistic scenes where object arrangements obey both physics and common sense. In our extensive experimental evaluation ScanEdit outperforms state of the art and demonstrates excellent re- sults for a variety of real-world scenes and input instruc- tions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15049 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ScanEdit: Hierarchically-Guided Functional 3D Scan Editing Boudjoghra, Mohamed el amine Laptev, Ivan Dai, Angela Computer Vision and Pattern Recognition With the fast pace of 3D capture technology and resulting abundance of 3D data, effective 3D scene editing becomes essential for a variety of graphics applications. In this work we present ScanEdit, an instruction-driven method for functional editing of complex, real-world 3D scans. To model large and interdependent sets of ob- jectswe propose a hierarchically-guided approach. Given a 3D scan decomposed into its object instances, we first construct a hierarchical scene graph representation to enable effective, tractable editing. We then leverage reason- ing capabilities of Large Language Models (LLMs) and translate high-level language instructions into actionable commands applied hierarchically to the scene graph. Fi- nally, ScanEdit integrates LLM-based guidance with ex- plicit physical constraints and generates realistic scenes where object arrangements obey both physics and common sense. In our extensive experimental evaluation ScanEdit outperforms state of the art and demonstrates excellent re- sults for a variety of real-world scenes and input instruc- tions. |
| title | ScanEdit: Hierarchically-Guided Functional 3D Scan Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.15049 |