DragD3D: Realistic Mesh Editing with Rigidity Control Driven by 2D Diffusion Priors

被引：0

作者：

Xie, Tianhao ^{[1
]}

Belilovsky, Eugene ^{[2
]}

Mudur, Sudhir ^{[1
]}

Popa, Tiberiu ^{[1
]}

机构：

[1] Concordia University, Montreal, Canada

[2] Concordia University, MILA, Montreal, Canada

来源：

arXiv | 2023年

关键词：

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Deep learning - Mathematical transformations - Shape optimization

引用

共 4 条

[1] As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors
KAIST, Korea, Republic of
不详
arXiv, 1600,
[2] Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
TTI-Chicago, United States
不详
Proc IEEE Comput Soc Conf Comput Vision Pattern Recognit, 1600, (12619-12629):
[3] Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation
Hong, Susung
Ahn, Donghoon
Kim, Seungryong
Advances in Neural Information Processing Systems, 2023, 36
[4] Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyond
Armandpour, Mohammadreza
Zheng, Huangjie
Sadeghian, Ali
Sadeghian, Amir
Zhou, Mingyuan
arXiv, 2023,