SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing

TL;DR

SimAvatar is a novel framework that generates highly realistic, simulation-ready 3D human avatars with layered hair and clothing from text prompts, enabling dynamic motion and realistic textures for simulation applications.

Contribution

We introduce a two-stage method combining 3D generative models and 3D Gaussians to produce fully simulation-ready avatars from text, surpassing existing approaches in realism and adaptability.

Findings

Produces highly realistic, textured 3D avatars.

Enables dynamic motion transfer via physics simulation.

First method to generate fully simulation-ready 3D avatars from text.

Abstract

We introduce SimAvatar, a framework designed to generate simulation-ready clothed 3D human avatars from a text prompt. Current text-driven human avatar generation methods either model hair, clothing, and the human body using a unified geometry or produce hair and garments that are not easily adaptable for simulation within existing simulation pipelines. The primary challenge lies in representing the hair and garment geometry in a way that allows leveraging established prior knowledge from foundational image diffusion models (e.g., Stable Diffusion) while being simulation-ready using either physics or neural simulators. To address this task, we propose a two-stage framework that combines the flexibility of 3D Gaussians with simulation-ready hair strands and garment meshes. Specifically, we first employ three text-conditioned 3D generative models to generate garment mesh, body shape and hair strands from the given text prompt. To leverage prior knowledge from foundational diffusion models, we attach 3D Gaussians to the body mesh, garment mesh, as well as hair strands and learn the avatar appearance through optimization. To drive the avatar given a pose sequence, we first apply physics simulators onto the garment meshes and hair strands. We then transfer the motion onto 3D Gaussians through carefully designed mechanisms for each body part. As a result, our synthesized avatars have vivid texture and realistic dynamic motion. To the best of our knowledge, our method is the first to produce highly realistic, fully simulation-ready 3D avatars, surpassing the capabilities of current approaches.