尽可能合理：使用二维扩散先验的合理性感知网格变形
As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors
AI总结：
本文提出APAP网格变形技术，利用二维扩散先验和分数蒸馏采样，在用户控制变形下保持网格合理性，并通过LoRA微调保持身份特征，实验证明其优于传统几何保持或畸变最小化方法。
摘要：
我们提出了As-Plausible-as-Possible（APAP）网格变形技术，该技术利用二维扩散先验在用户控制的变形下保持网格的合理性。我们的框架使用逐面雅可比矩阵来表示网格变形，其中网格顶点坐标通过可微分的泊松求解计算。变形后的网格被渲染，生成的二维图像用于分数蒸馏采样（SDS）过程，该过程能够从预训练的二维扩散模型中提取有意义的合理性先验。为了更好地保持编辑后网格的身份特征，我们使用LoRA对二维扩散模型进行微调。由SDS提取的梯度和用户指定的控制柄位移随后反向传播到逐面雅可比矩阵，我们使用迭代梯度下降来计算最终变形，以在用户编辑和输出合理性之间取得平衡。我们在二维和三维网格上评估了我们的方法，并证明了与先前技术使用的几何保持或畸变最小化先验相比，使用合理性先验在定性和定量上均有改进。我们的项目页面位于：https://as-plausible-aspossible.github.io/
英文摘要：
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/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
