Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts
This addresses a bottleneck in text-to-3D generation for users needing detailed and interactive 3D content from complex descriptions, representing an incremental improvement over existing methods.
The paper tackles the problem of generating accurate 3D content from complex text prompts involving multiple objects with attributes, proposing Progressive3D, a framework that uses progressive local editing and overlapped semantic component suppression to achieve precise results, as demonstrated in extensive experiments.
Recent text-to-3D generation methods achieve impressive 3D content creation capacity thanks to the advances in image diffusion models and optimizing strategies. However, current methods struggle to generate correct 3D content for a complex prompt in semantics, i.e., a prompt describing multiple interacted objects binding with different attributes. In this work, we propose a general framework named Progressive3D, which decomposes the entire generation into a series of locally progressive editing steps to create precise 3D content for complex prompts, and we constrain the content change to only occur in regions determined by user-defined region prompts in each editing step. Furthermore, we propose an overlapped semantic component suppression technique to encourage the optimization process to focus more on the semantic differences between prompts. Extensive experiments demonstrate that the proposed Progressive3D framework generates precise 3D content for prompts with complex semantics and is general for various text-to-3D methods driven by different 3D representations.