LucidDreamer：透過區間分數匹配實現高保真度文本生成3D。

LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching

November 19, 2023

作者: Yixun Liang, Xin Yang, Jiantao Lin, Haodong Li, Xiaogang Xu, Yingcong Chen

cs.AI

摘要

最近在文本轉3D生成方面的進展標誌著生成模型中的一個重要里程碑，為在各種現實場景中創建富有想像力的3D資產開啟了新的可能性。儘管最近在文本轉3D生成方面取得了一些進展，但往往在渲染詳細和高質量的3D模型方面表現不佳。這個問題特別普遍，因為許多方法基於得分蒸餾取樣（SDS）。本文識別出SDS存在一個顯著缺陷，即為3D模型帶來不一致和低質量的更新方向，導致過度平滑效應。為解決這個問題，我們提出了一種名為區間得分匹配（ISM）的新方法。ISM採用確定性擴散軌跡，並利用基於區間的得分匹配來抵消過度平滑。此外，我們將3D高斯擴散技術納入我們的文本轉3D生成流程中。大量實驗表明，我們的模型在質量和訓練效率方面大大優於當前的最新技術。

English

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.