PoseAlign: Sculpting Pose-Consistent Meshes via Text-Guided Deformation

2026-07-12

AI Summary

This work addresses the challenge of text-guided 3D mesh deformation, where achieving semantic alignment with the input text while preserving the original pose remains difficult. The authors propose a two-stage deformation strategy: first, a smooth global pose scaling is performed using a differentiable Laplacian representation; second, local geometric details are refined through a pose-aligned Score Distillation Sampling (SDS) loss combined with an attention-sharing mechanism. This approach effectively maintains pose consistency of the input mesh while significantly enhancing semantic fidelity to the guiding text and improving controllability of the deformation. Experimental results demonstrate that the method outperforms existing techniques in both generation quality and geometric fidelity.

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

Problem

• mesh deformation
• text-guided
• pose preservation
• 3D generation
• shape manipulation

Innovation

• PoseAlign
• text-guided deformation
• Laplacian representation
• pose-aligned SDS loss
• attention-sharing mechanism