VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder
It addresses the problem of flexible 3D content creation for applications like gaming or design, though it appears incremental by building on existing diffusion and volumetric methods.
The paper tackles text-to-3D generation by introducing a volumetric encoder and diffusion model, achieving promising results in producing diverse and recognizable 3D samples from text prompts on the Objaverse dataset.
This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view images. The 3D volumes are then trained on a diffusion model for text-to-3D generation using a 3D U-Net. This research further addresses the challenges of inaccurate object captions and high-dimensional feature volumes. The proposed model, trained on the public Objaverse dataset, demonstrates promising outcomes in producing diverse and recognizable samples from text prompts. Notably, it empowers finer control over object part characteristics through textual cues, fostering model creativity by seamlessly combining multiple concepts within a single object. This research significantly contributes to the progress of 3D generation by introducing an efficient, flexible, and scalable representation methodology.