Large-scale, high-quality dynamic 3D (4D) assets are essential for learning physically grounded representations, but remain costly to capture and annotate at scale. This limits the viability of supervised 4D learning and motivates zero-shot text-to-4D generation leveraging pretrained diffusion priors. To model complex dynamics, prior methods typically adopt implicit 3D representations (e.g., NeRFs or 3DGS) for their deformation capacity. However, their implicit nature provides limited control over surface topology, which hinders high-fidelity geometry and makes temporally coherent surface reconstruction challenging. To address these limitations, we explore zero-shot text-to-4D mesh generation. However, a structural mismatch arises when combining diffusion-based guidance with topology-constrained meshes: the guidance is noisy and spatially inconsistent, while meshes impose severe topological constraints, making direct vertex-level deformation unstable. In this paper, we introduce TextMesh4D, the first zero-shot framework for text-to-4D that directly generates dynamic meshes by addressing the above challenge at two complementary levels. Geometrically, we shift deformation modeling from vertices to faces via a Jacobian Deformation Field (JDF), enabling topology-aware surface reconstruction through an integrability-enforcing integration formulation. Semantically, we propose a Local-Global Semantic Regularizer (LGSR) that preserves identity over time by jointly constraining local deformation plausibility and global shape consistency. Extensive experiments demonstrate state-of-the-art temporal consistency, structural fidelity, and visual quality, while remaining efficient on a single 24GB GPU.

翻译：大规模、高质量的动态三维（4D）资产对于学习基于物理的表达至关重要，但其获取和标注成本高昂，限制了监督式4D学习的可行性，从而推动了利用预训练扩散先验的零样本文本到4D生成方法的发展。为建模复杂动态，现有方法通常采用隐式3D表示（如NeRF或3DGS）以利用其变形能力。然而，隐式表示对表面拓扑的控制有限，难以实现高保真几何结构，且使得时间一致的表面重构面临挑战。针对上述限制，我们探索了零样本文本到4D网格生成。然而，当结合基于扩散的引导与拓扑约束网格时，出现了结构不匹配问题：引导信号具有噪声且空间不一致，而网格施加了严格的拓扑约束，导致直接进行顶点级变形不稳定。本文提出TextMesh4D——首个直接生成动态网格的文本到4D零样本框架，通过两个互补层面解决上述挑战。在几何层面，我们引入雅可比变形场（JDF）将变形建模从顶点迁移至面片，并通过可积性约束的积分公式实现拓扑感知的表面重构；在语义层面，提出局部-全局语义正则化器（LGSR），通过联合约束局部变形合理性与全局形状一致性来保持时序身份特征。大量实验表明，该方法在单张24GB GPU上高效运行的同时，在时间一致性、结构保真度和视觉质量方面均达到最优水平。