Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.03256 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908750279868416 |
|---|---|
| author | Lu, Hexiao Sun, Xiaokun Cai, Zeyu Guo, Hao Tai, Ying Yang, Jian Zhang, Zhenyu |
| author_facet | Lu, Hexiao Sun, Xiaokun Cai, Zeyu Guo, Hao Tai, Ying Yang, Jian Zhang, Zhenyu |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03256 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training Lu, Hexiao Sun, Xiaokun Cai, Zeyu Guo, Hao Tai, Ying Yang, Jian Zhang, Zhenyu Computer Vision and Pattern Recognition 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/. |
| title | Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.03256 |