As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yoo, Seungwoo, Kim, Kunho, Kim, Vladimir G., Sung, Minhyuk
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911819835113472
author Yoo, Seungwoo
Kim, Kunho
Kim, Vladimir G.
Sung, Minhyuk
author_facet Yoo, Seungwoo
Kim, Kunho
Kim, Vladimir G.
Sung, Minhyuk
contents We present As-Plausible-as-Possible (APAP) mesh deformation technique that leverages 2D diffusion priors to preserve the plausibility of a mesh under user-controlled deformation. Our framework uses per-face Jacobians to represent mesh deformations, where mesh vertex coordinates are computed via a differentiable Poisson Solve. The deformed mesh is rendered, and the resulting 2D image is used in the Score Distillation Sampling (SDS) process, which enables extracting meaningful plausibility priors from a pretrained 2D diffusion model. To better preserve the identity of the edited mesh, we fine-tune our 2D diffusion model with LoRA. Gradients extracted by SDS and a user-prescribed handle displacement are then backpropagated to the per-face Jacobians, and we use iterative gradient descent to compute the final deformation that balances between the user edit and the output plausibility. We evaluate our method with 2D and 3D meshes and demonstrate qualitative and quantitative improvements when using plausibility priors over geometry-preservation or distortion-minimization priors used by previous techniques. Our project page is at: https://as-plausible-aspossible.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2311_16739
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors
Yoo, Seungwoo
Kim, Kunho
Kim, Vladimir G.
Sung, Minhyuk
Computer Vision and Pattern Recognition
Graphics
We present As-Plausible-as-Possible (APAP) mesh deformation technique that leverages 2D diffusion priors to preserve the plausibility of a mesh under user-controlled deformation. Our framework uses per-face Jacobians to represent mesh deformations, where mesh vertex coordinates are computed via a differentiable Poisson Solve. The deformed mesh is rendered, and the resulting 2D image is used in the Score Distillation Sampling (SDS) process, which enables extracting meaningful plausibility priors from a pretrained 2D diffusion model. To better preserve the identity of the edited mesh, we fine-tune our 2D diffusion model with LoRA. Gradients extracted by SDS and a user-prescribed handle displacement are then backpropagated to the per-face Jacobians, and we use iterative gradient descent to compute the final deformation that balances between the user edit and the output plausibility. We evaluate our method with 2D and 3D meshes and demonstrate qualitative and quantitative improvements when using plausibility priors over geometry-preservation or distortion-minimization priors used by previous techniques. Our project page is at: https://as-plausible-aspossible.github.io/
title As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2311.16739