arrow
返回

FusionDeformer: text-guided mesh deformation using diffusion models

delete2024-05-25
delete1
PRE
AI
H
Hao Xu
Y
Yiqian Wu
X
Xiangjun Tang
张
张静 (Jing Zhang)
Z
Zhebin Zhang
李
李琛 (Chen Li)
DOI:10.1007/s00371-024-03463-7delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Mesh deformation has a wide range of applications, including character creation, geometry modelling, deforming animation, and morphing. Recently, mesh deformation methods based on CLIP models demonstrated the ability to perform automatic text-guided mesh deformation. However, using 2D guidance to deform a 3D mesh attempts to solve an ill-posed problem and leads to distortion and unsmoothness, which cannot be eliminated by CLIP-based methods because they focus on semantic-aware features and cannot identify these artefacts. To this end, we propose FusionDeformer, a novel automatic text-guided mesh deformation method that leverages diffusion models. The deformation is achieved by Score Distillation Sampling, which minimizes the KL-divergence between the distribution of rendered deformed mesh and the text-conditioned distribution. To alleviate the intrinsic ill-posed problem, we incorporate two approaches into our framework. The first approach involves combining multiple orthogonal views into a single image, providing robust deformation while avoiding the need for additional memory. The second approach incorporates a new regularization to address the unsmooth artefacts. Our experimental results show that the proposed method can generate high-quality, smoothly deformed meshes that align precisely with the input text description while preserving the topological relationships. Additionally, our method offers a text2morphing approach to animation design, enabling common users to produce special effects animation.
Keyword:
Diffusion model
Mesh deformation
Score Distillation Sampling

期刊

Visual Computer 封面图
Visual Computer
IF:
2.9
论文数:
4.6K
被引数:
6.5K

机构

Z
zhejiang university
学者数:
17.7W
论文数: 12.1W
被引数: 152
引用论文

引用论文

Interspecific potato somatic hybrids between Solanum malmeanum and S. tuberosum provide valuable resources for freezing-tolerance breeding
err2021-06-25
err0
PREAI
errWei Tu; Jianke Dong; Ying Zou; Qinghao Zhao; Haibo Wang; Jingwen Ying; Jianghai Wu; Juan Du; Xingkui Cai; Botao Song
err分享
err收藏
err分享
err收藏
iWIRES: An Analyze-and-Edit Approach to Shape Manipulation
err2009-07-27
err213
PREAI
errGal, Ran; Sorkine, Olga; Mitra, Niloy J.; Cohen-Or, Daniel
err分享
err收藏
ALIG Net: Partial-Shape Agnostic Alignment via Unsupervised Learning
err2018-12-14
err139
PREAI
errHanocka, Rana; Fish, Noa; Wang, Zhenhua; Giryes, Raja; Fleishman, Shachar; Cohen-Or, Daniel
err分享
err收藏
Learning Contact Corrections for Handle-Based Subspace Dynamics
err2021-07-19
err2
errOAAI
errRomero, Cristian; Casas, Dan; Perez, Jesus; Otaduy, Miguel
err分享
err收藏
学者 查看更多内容