Progressive Text-to-3D Generation for Automatic 3D Prototyping
This work addresses the problem of efficient and detailed text-to-3D generation for users in 3D prototyping, offering a more natural interaction method, but it appears incremental as it builds on progressive learning concepts.
The paper tackles the challenge of generating detailed 3D objects from text descriptions by proposing a Multi-Scale Triplane Network and progressive learning strategy, which outperforms existing methods in recovering fine-grained details and optimizing large 3D outputs, especially for difficult descriptions.
Text-to-3D generation is to craft a 3D object according to a natural language description. This can significantly reduce the workload for manually designing 3D models and provide a more natural way of interaction for users. However, this problem remains challenging in recovering the fine-grained details effectively and optimizing a large-size 3D output efficiently. Inspired by the success of progressive learning, we propose a Multi-Scale Triplane Network (MTN) and a new progressive learning strategy. As the name implies, the Multi-Scale Triplane Network consists of four triplanes transitioning from low to high resolution. The low-resolution triplane could serve as an initial shape for the high-resolution ones, easing the optimization difficulty. To further enable the fine-grained details, we also introduce the progressive learning strategy, which explicitly demands the network to shift its focus of attention from simple coarse-grained patterns to difficult fine-grained patterns. Our experiment verifies that the proposed method performs favorably against existing methods. For even the most challenging descriptions, where most existing methods struggle to produce a viable shape, our proposed method consistently delivers. We aspire for our work to pave the way for automatic 3D prototyping via natural language descriptions.