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

Yixun Liang, Xin Yang, Jiantao Lin, Haodong Li, Xiaogang Xu, Yingcong Chen; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 6517-6526

Abstract


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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2024_CVPR, author = {Liang, Yixun and Yang, Xin and Lin, Jiantao and Li, Haodong and Xu, Xiaogang and Chen, Yingcong}, title = {LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6517-6526} }