BodyShapeGPT: SMPL Body Shape Manipulation with LLMs

TL;DR

This paper introduces BodyShapeGPT, a method that fine-tunes LLMs to understand and manipulate 3D human body shapes using natural language, enabling more intuitive avatar customization.

Contribution

It presents a novel approach to control SMPL-X body shape parameters through fine-tuned LLMs, bridging natural language and 3D avatar modeling.

Findings

LLMs can accurately infer SMPL shape parameters from textual descriptions.

The method enables natural language-based manipulation of 3D human shapes.

This approach enhances human-computer interaction in virtual environments.

Abstract

Generative AI models provide a wide range of tools capable of performing complex tasks in a fraction of the time it would take a human. Among these, Large Language Models (LLMs) stand out for their ability to generate diverse texts, from literary narratives to specialized responses in different fields of knowledge. This paper explores the use of fine-tuned LLMs to identify physical descriptions of people, and subsequently create accurate representations of avatars using the SMPL-X model by inferring shape parameters. We demonstrate that LLMs can be trained to understand and manipulate the shape space of SMPL, allowing the control of 3D human shapes through natural language. This approach promises to improve human-machine interaction and opens new avenues for customization and simulation in virtual environments.