mlsanityData to 7 Oct 2026

BodyShapeGPT: SMPL Body Shape Manipulation with LLMs

arXiv 2410.03556 ↗First posted 18 Sep 2024cs.CL cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 19 of its 23 references that are in the map. First posted on arXiv 18 Sep 2024.

Builds on

19 of 23 references.

References · 19

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  4. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  5. 2023MotionGPT: Human Motion as a Foreign Languagecited by 521
  6. 2022MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesiscited by 218
  7. 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Modelscited by 154
  8. 2022InstantAvatar: Learning Avatars from Monocular Video in 60 Secondscited by 138
  9. 2018Detailed Human Avatars from Monocular Videocited by 109
  10. 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecastingcited by 78
  11. 2023ChatPose: Chatting about 3D Human Posecited by 71
  12. 2023AG3D: Learning to Generate 3D Avatars from 2D Image Collectionscited by 55
7 more
  1. 2022Accurate 3D Body Shape Regression using Metric and Semantic Attributescited by 49
  2. 2023FitMe: Deep Photorealistic 3D Morphable Model Avatarscited by 38
  3. 2023AvatarBooth: High-Quality and Customizable 3D Human Avatar Generationcited by 37
  4. 2023SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Imagecited by 30
  5. 2023StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generationcited by 25
  6. 2023POCO: 3D Pose and Shape Estimation with Confidencecited by 20
  7. 2023HAVE-FUN: Human Avatar Reconstruction from Few-Shot Unconstrained Imagescited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 1.

6 papers.

  1. 2025PromptHMR: Promptable Human Mesh Recoverycited by 70
  2. 2025Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motionscited by 11
  3. 2024SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothingcited by 9
  4. 2025Towards Fine-Grained Human Motion Video Captioningcited by 3
  5. 2025Scalable RF Simulation in Generative 4D Worldscited by 2
  6. 2026Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motioncited by 0