Muses：无需训练地设计、组合与生成不存在的奇幻 3D 生物
Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training
用 3D 骨骼作为结构先验，把「设计—组装—生成」拆成可复用的免训练流水线；其中图约束推理构造骨骼、潜空间体素组装、骨骼条件下的图像引导外观建模，都可迁移到 3D 资产编辑与组合式生成。
原文依据 Muses leverages the 3D skeleton--a fundamental representation of biological forms--to explicitly and rationally compose diverse elements.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 Muses，首个以前馈范式进行奇幻 3D 生物生成的免训练方法。此前的方法依赖部件感知优化、手工组装或 2D 图像生成，由于部件级精细操作困难且域外生成能力有限，往往产生不真实或不连贯的 3D 资产。相比之下，Muses 利用 3D 骨骼——生物形态的一种基础表示——来显式且合理地组合多样元素。这一骨骼基础将 3D 内容创建形式化为一个结构感知的「设计、组合、生成」流水线。Muses 首先通过图约束推理构造一个在布局与尺度上连贯、且富有创意的组合式 3D 骨骼。该骨骼随后在结构化潜变量空间中引导基于体素的组装过程，整合来自不同物体的区域。最后，在骨骼条件下进行图像引导的外观建模，为组装后的形状生成风格一致且和谐的纹理。大量实验表明，Muses 在视觉保真度与文本描述对齐方面达到最优性能，并在灵活的 3D 物体编辑上具有潜力。
英文原文摘要 1241 字符
We present Muses, the first training-free method for fantastic 3D creature generation in a feed-forward paradigm. Previous methods, which rely on part-aware optimization, manual assembly, or 2D image generation, often produce unrealistic or incoherent 3D assets due to the challenges of intricate part-level manipulation and limited out-of-domain generation. In contrast, Muses leverages the 3D skeleton--a fundamental representation of biological forms--to explicitly and rationally compose diverse elements. This skeletal foundation formalizes 3D content creation as a structure-aware pipeline of design, composition, and generation. Muses begins by constructing a creatively composed 3D skeleton with coherent layout and scale through graph-constrained reasoning. This skeleton then guides a voxel-based assembly process within a structured latent space, integrating regions from different objects. Finally, image-guided appearance modeling under skeletal conditions is applied to generate a style-consistent and harmonious texture for the assembled shape. Extensive experiments establish Muses' state-of-the-art performance in terms of visual fidelity and alignment with textual descriptions, and potential on flexible 3D object editing.