Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation
This addresses the challenge of generating 3D assets without large-scale 3D training data, which is beneficial for applications in computer graphics and AI, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of limited quality and generalizability in 3D content generation by introducing Kiss3DGen, a framework that repurposes a 2D image diffusion model to generate 3D assets, resulting in efficient production of high-quality 3D models.
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.