HumanCoser: Layered 3D Human Generation via Semantic-Aware Diffusion Model

TL;DR

This paper introduces a novel layered 3D human generation method from text prompts, enabling complex clothing and virtual try-on with a physically-decoupled diffusion model and multi-layer rendering.

Contribution

It proposes a layer-wise dressed human representation with a dual-representation decoupling framework and an SMPL-driven deformation network for flexible clothing transfer.

Findings

Achieves state-of-the-art layered 3D human generation

Supports virtual try-on and layered human animation

Handles complex clothing with physical decoupling

Abstract

This paper aims to generate physically-layered 3D humans from text prompts. Existing methods either generate 3D clothed humans as a whole or support only tight and simple clothing generation, which limits their applications to virtual try-on and part-level editing. To achieve physically-layered 3D human generation with reusable and complex clothing, we propose a novel layer-wise dressed human representation based on a physically-decoupled diffusion model. Specifically, to achieve layer-wise clothing generation, we propose a dual-representation decoupling framework for generating clothing decoupled from the human body, in conjunction with an innovative multi-layer fusion volume rendering method. To match the clothing with different body shapes, we propose an SMPL-driven implicit field deformation network that enables the free transfer and reuse of clothing. Extensive experiments demonstrate that our approach not only achieves state-of-the-art layered 3D human generation with complex clothing but also supports virtual try-on and layered human animation.