Kiss3DGen:
Repurposing Image Diffusion Models for 3D Asset Generation

Jiantao Lin

1*,  

Xin Yang

1,2*,  

Meixi Chen

1*,  

Yingjie Xu

1,  

Dongyu Yan

1,  

Leyi Wu

1,  

Xinli Xu

1,  

Lie XU

3,  

Shunsi Zhang

3,  

Ying-Cong Chen

1,2†,  

1 HKUST(GZ)

,

2 HKUST

,

3 Guangzhou Quwan Network Technology

* Equal contribution

† Corresponding author

Arxiv Demo (HF) Demo (Envision) Code

In collaboration with Quwan, this project has been successfully commercialized and is now available for real-world applications (See 趣丸万相 for details). We are truly grateful to Quwan for their support, especially in data and engineering, which were key to this achievement.

Abstract

Diffusion models have achieved great success in generating 2D images. However, the quality and generalizability of 3D content generation remain limited. State-of-the-art methods often require large-scale 3D assets for training, which are challenging to collect. In this work, we introduce Kiss3DGen (Keep It Simple and Straightforward in 3D Generation), an efficient framework for generating, editing, and enhancing 3D objects by repurposing a well-trained 2D image diffusion model for 3D generation. Specifically, we fine-tune a diffusion model to generate "3D Bundle Image", a tiled representation composed of multi-view images and their corresponding normal maps. The normal maps are then used to reconstruct a 3D mesh, and the multi-view images provide texture mapping, resulting in a complete 3D model. This simple method effectively transforms the 3D generation problem into a 2D image generation task, maximizing the utilization of knowledge in pretrained diffusion models. Furthermore, we demonstrate that our Kiss3DGen model is compatible with various diffusion model techniques, enabling advanced features such as 3D editing, mesh and texture enhancement, etc. Through extensive experiments, we demonstrate the effectiveness of our approach, showcasing its ability to produce high-quality 3D models efficiently.

Text-to-Mesh

Image-to-Mesh

Input Image

Generated Mesh

Mesh Refinement Gallery

BibTeX


        @article{lin2025kiss3dgenrepurposingimagediffusion,
            title={Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation},
            author={Jiantao Lin, Xin Yang, Meixi Chen, Yingjie Xu, Dongyu Yan, Leyi Wu, Xinli Xu, Lie XU, Shunsi Zhang, Ying-Cong Chen},
            journal={arXiv preprint arXiv:2503.01370},
            year={2025}
          }