先走再跳舞：通过生成性遮蔽动作先验实现高保真可编辑舞蹈合成
Walk Before You Dance: High-fidelity and Editable Dance Synthesis via Generative Masked Motion Prior
AI总结：
本研究提出一种生成性遮蔽动作先验模型，实现高保真且可编辑的舞蹈合成，通过多塔结构提升动作生成质量与编辑能力。
摘要：
近期舞蹈生成领域的发展使得自动合成3D舞蹈动作成为可能。然而，现有方法在同时实现高真实感、精确的舞蹈-音乐同步、多样的动作表达和物理合理性方面仍面临重大挑战。为解决这些限制，我们提出了一种新的方法，利用生成性遮蔽文本到动作模型作为分布先验，学习从多样化的引导信号（包括音乐、类型和姿态）到高质量舞蹈动作序列的概率映射。我们的框架还支持语义动作编辑，如动作修复和身体部分修改。具体来说，我们引入了一个多塔遮蔽动作模型，该模型整合了一个文本条件遮蔽动作主干和两个并行的模态特定分支：音乐引导塔和姿态引导塔。模型通过同步和渐进的遮蔽训练进行训练，这使得预训练的文本到动作先验能够有效融入舞蹈合成过程，同时允许每个引导分支通过自己的损失函数独立优化，从而减轻梯度干扰。在推理过程中，我们引入了分类器自由logits引导和姿态引导的token优化，以加强音乐、类型和姿态信号的影响。广泛的实验表明，我们的方法在舞蹈生成方面设立了新的状态，显著提高了质量和可编辑性，比现有方法有了显著的进步。项目页面可在https://foram-s1.github.io/DanceMosaic/上查看。
英文摘要：
Recent advances in dance generation have enabled the automatic synthesis of 3D dance motions. However, existing methods still face significant challenges in simultaneously achieving high realism, precise dance-music synchronization, diverse motion expression, and physical plausibility. To address these limitations, we propose a novel approach that leverages a generative masked text-to-motion model as a distribution prior to learn a probabilistic mapping from diverse guidance signals, including music, genre, and pose, into high-quality dance motion sequences. Our framework also supports semantic motion editing, such as motion inpainting and body part modification. Specifically, we introduce a multi-tower masked motion model that integrates a text-conditioned masked motion backbone with two parallel, modality-specific branches: a music-guidance tower and a pose-guidance tower. The model is trained using synchronized and progressive masked training, which allows effective infusion of the pretrained text-to-motion prior into the dance synthesis process while enabling each guidance branch to optimize independently through its own loss function, mitigating gradient interference. During inference, we introduce classifier-free logits guidance and pose-guided token optimization to strengthen the influence of music, genre, and pose signals. Extensive experiments demonstrate that our method sets a new state of the art in dance generation, significantly advancing both the quality and editability over existing approaches. Project Page available at https://foram-s1.github.io/DanceMosaic/
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。
