PoseAlign: Sculpting Pose-Consistent Meshes via Text-Guided Deformation
arXiv:2607.10560
PoseAlign introduces a two-stage method for text-guided 3D mesh deformation that first scales the mesh globally to preserve its pose and then sculpts local details, using a differentiable Laplacian representation and a pose‑aligned score distillation sampling loss.
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
CGI 2026 Best Paper Award. Project page: https://cousingrade6.github.io/PoseAlign