CMD: Controllable Multiview Diffusion for 3D Editing and Progressive Generation

TL;DR

CMD introduces a controllable 3D generation method that allows local editing of components by formulating it as a conditional multiview diffusion process, enabling flexible modifications without regenerating the entire model.

Contribution

The paper presents a novel conditional multiview diffusion approach for 3D generation that supports local editing and component-wise control, improving flexibility and quality.

Findings

Enables part-by-part 3D model generation.

Supports local editing based on input image revisions.

Improves generation quality through component decomposition.

Abstract

Recently, 3D generation methods have shown their powerful ability to automate 3D model creation. However, most 3D generation methods only rely on an input image or a text prompt to generate a 3D model, which lacks the control of each component of the generated 3D model. Any modifications of the input image lead to an entire regeneration of the 3D models. In this paper, we introduce a new method called CMD that generates a 3D model from an input image while enabling flexible local editing of each component of the 3D model. In CMD, we formulate the 3D generation as a conditional multiview diffusion model, which takes the existing or known parts as conditions and generates the edited or added components. This conditional multiview diffusion model not only allows the generation of 3D models part by part but also enables local editing of 3D models according to the local revision of the input image without changing other 3D parts. Extensive experiments are conducted to demonstrate that CMD decomposes a complex 3D generation task into multiple components, improving the generation quality. Meanwhile, CMD enables efficient and flexible local editing of a 3D model by just editing one rendered image.