PoseAlign: Sculpting Pose-Consistent Meshes via Text-Guided Deformation
2026-07-12 • Graphics
GraphicsComputer Vision and Pattern Recognition
AI summaryⓘ
The authors present PoseAlign, a method to change 3D mesh shapes based on text instructions while keeping their original pose. They split the process into two parts: scaling the overall pose smoothly using a special mesh math tool called the Laplacian, and then adding fine details with a new loss function that helps keep the pose stable. Their approach improves the balance between following the text and maintaining the original shape. Tests show their method works well compared to others.
3D mesh deformationLaplacian mesh representationpose preservationtext-guided deformationscore distillation sampling (SDS)attention mechanismglobal pose scalinglocal detail sculpting
Authors
Shijin Wang, Zichong Chen, Yang Zhou, Hui Huang
Abstract
Mesh deformation, the process of altering the vertex positions of a 3D mesh while preserving its topological structure, is a cornerstone of computer graphics. Despite the recent emergence of numerous text-guided 3D mesh deformation methods, deforming an initial mesh into one that both adheres to text prompts and preserves its pose remains challenging. This paper proposes PoseAlign, which decomposes text-guided mesh deformation into two stages: global pose scaling and local detail sculpting. Specifically, in the first stage, we introduce the Laplacian as a differentiable mesh representation to enable more efficient yet smoother global deformation. Then, we propose a novel pose-aligned SDS loss by adapting score distillation sampling (SDS) with an attention-sharing mechanism, which sculptures fine-grained geometric details for the deformed mesh while preserving its original pose. PoseAlign significantly enhances the controllability of the overall deformation process, achieving a favorable balance between pose preservation and text alignment. Experiments demonstrate the competitive advantages of our method in text alignment and mesh quality. Code is available at: https://cousingrade6.github.io/PoseAlign