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.

翻译：文本到3D生成的最新进展标志着生成模型的一个重要里程碑，为在各类真实场景中创建富有想象力的3D资产开启了新的可能性。尽管近期文本到3D生成技术取得了显著进展，但它们在生成细节丰富且高质量的3D模型方面仍存在不足。这一问题在众多基于得分蒸馏采样（SDS）的方法中尤为突出。本文揭示了SDS的一个显著缺陷：其为3D模型提供的更新方向不一致且质量低下，导致过度平滑效应。为解决这一问题，我们提出了一种名为区间得分匹配（ISM）的新方法。ISM利用确定性扩散轨迹，并采用基于区间的得分匹配来抑制过度平滑。此外，我们将3D高斯溅射（3D Gaussian Splatting）集成到文本到3D生成流程中。大量实验表明，我们的模型在质量和训练效率上均大幅超越当前最优方法。