ParSEL: Parameterized Shape Editing with Language

TL;DR

ParSEL is a system that enables precise, controllable 3D shape editing from natural language by inferring parameterized editing programs using large-language models and an analytical propagation algorithm.

Contribution

It introduces a novel method combining LLMs and analytical algorithms to generate complete, semantically consistent 3D editing programs from natural language requests.

Findings

ParSEL effectively produces controllable 3D shape edits from natural language.

The Analytical Edit Propagation algorithm extends initial edits to complete programs.

ParSEL outperforms alternative methods in shape editing accuracy and control.

Abstract

The ability to edit 3D assets from natural language presents a compelling paradigm to aid in the democratization of 3D content creation. However, while natural language is often effective at communicating general intent, it is poorly suited for specifying precise manipulation. To address this gap, we introduce ParSEL, a system that enables controllable editing of high-quality 3D assets from natural language. Given a segmented 3D mesh and an editing request, ParSEL produces a parameterized editing program. Adjusting the program parameters allows users to explore shape variations with a precise control over the magnitudes of edits. To infer editing programs which align with an input edit request, we leverage the abilities of large-language models (LLMs). However, while we find that LLMs excel at identifying initial edit operations, they often fail to infer complete editing programs, and produce outputs that violate shape semantics. To overcome this issue, we introduce Analytical Edit Propagation (AEP), an algorithm which extends a seed edit with additional operations until a complete editing program has been formed. Unlike prior methods, AEP searches for analytical editing operations compatible with a range of possible user edits through the integration of computer algebra systems for geometric analysis. Experimentally we demonstrate ParSEL's effectiveness in enabling controllable editing of 3D objects through natural language requests over alternative system designs.