无需训练即可生成幻想3D生物，靠骨骼结构组合实现真实感
Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training
- 用生物骨骼结构作为基础，理性组合不同部件
- 生成物体与文本描述匹配度高，视觉保真度领先
- 适合游戏/影视从业者快速设计奇幻角色
我们提出 Muses，首个无需训练的前馈式幻想3D生物生成方法。以往方法依赖部件感知优化、手动拼装或2D图像生成，常因复杂部件操控和域外生成能力有限，导致结果不真实或不连贯。Muses 则利用3D骨骼这一生物形态的基础表示，显式且合理地组合多样元素，将3D内容创作形式化为结构感知的设计-组合-生成流程。Muses 首先通过图约束推理构建布局与尺度协调的创意3D骨骼；随后在结构化潜在空间中，基于体素进行部件集成；最后在骨骼约束下，通过图像引导的外观建模，生成风格一致且和谐的纹理。大量实验表明，Muses 在视觉保真度和文本对齐方面达到当前最优水平，并具备灵活的3D对象编辑潜力。
原文摘要 · Abstract (English)
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. Project page: https://luhexiao.github.io/Muses.github.io/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。