BAG: Body-Aligned 3D Wearable Asset Generation

TL;DR

BAG introduces a novel method for automatically generating 3D wearable assets aligned with human bodies by leveraging multiview diffusion models, Controlnet guidance, and physics simulation for accurate fitting.

Contribution

The paper presents a new approach combining multiview diffusion, Controlnet, and physics simulation to generate and fit 3D wearable assets onto human bodies, addressing a previously unexplored challenge.

Findings

Outperforms existing methods in shape diversity and quality

Demonstrates effective body-aligned 3D asset generation from images

Achieves accurate asset fitting with physics-based adjustments

Abstract

While recent advancements have shown remarkable progress in general 3D shape generation models, the challenge of leveraging these approaches to automatically generate wearable 3D assets remains unexplored. To this end, we present BAG, a Body-aligned Asset Generation method to output 3D wearable asset that can be automatically dressed on given 3D human bodies. This is achived by controlling the 3D generation process using human body shape and pose information. Specifically, we first build a general single-image to consistent multiview image diffusion model, and train it on the large Objaverse dataset to achieve diversity and generalizability. Then we train a Controlnet to guide the multiview generator to produce body-aligned multiview images. The control signal utilizes the multiview 2D projections of the target human body, where pixel values represent the XYZ coordinates of the body surface in a canonical space. The body-conditioned multiview diffusion generates body-aligned multiview images, which are then fed into a native 3D diffusion model to produce the 3D shape of the asset. Finally, by recovering the similarity transformation using multiview silhouette supervision and addressing asset-body penetration with physics simulators, the 3D asset can be accurately fitted onto the target human body. Experimental results demonstrate significant advantages over existing methods in terms of image prompt-following capability, shape diversity, and shape quality. Our project page is available at https://bag-3d.github.io/.