LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching
This addresses the challenge of generating high-fidelity 3D assets from text for applications in creative and real-world scenarios, representing a strong specific gain.
The paper tackled the problem of low-quality and over-smoothing in text-to-3D generation by proposing Interval Score Matching (ISM), which improved rendering details and training efficiency, outperforming state-of-the-art methods.
The recent advancements in text-to-3D generation mark a significant milestone in generative models, unlocking new possibilities for creating imaginative 3D assets across various real-world scenarios. While recent advancements in text-to-3D generation have shown promise, they often fall short in rendering detailed and high-quality 3D models. This problem is especially prevalent as many methods base themselves on Score Distillation Sampling (SDS). This paper identifies a notable deficiency in SDS, that it brings inconsistent and low-quality updating direction for the 3D model, causing the over-smoothing effect. To address this, we propose a novel approach called Interval Score Matching (ISM). ISM employs deterministic diffusing trajectories and utilizes interval-based score matching to counteract over-smoothing. Furthermore, we incorporate 3D Gaussian Splatting into our text-to-3D generation pipeline. Extensive experiments show that our model largely outperforms the state-of-the-art in quality and training efficiency.