Research map / 3D vision / 3D generation
Learning Hierarchical Hyperbolic Mixture Model for Part-aware 3D Generation
Qitong Yang, Mingtao Feng, Zijie Wu, Huixin Zhu, Weisheng Dong, Yaonan Wang, Ajmal Mian
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use hyperbolic space instead of Euclidean for semantics and sampling (ablation) | H2MM · ShapeNet | FID: 16.94 -> 12.26 | Improved |
| use hyperbolic space instead of Euclidean for semantics and sampling (ablation) | H2MM · ShapeNet | NLL: 1.21 -> 0.97 | Improved |
| decouple radial and angular noise in geodesic diffusion (ablation) | Hyperbolic diffusion · ShapeNet | FID: 16.72 -> 12.34 | Improved |
| decouple radial and angular noise in geodesic diffusion (ablation) | Hyperbolic diffusion · ShapeNet | CLIP-S: 27.36 -> 30.27 | Improved |
| add tree-topology network (ablation) | H2MM diffusion · ShapeNet | FID: 31.4 -> 27.1 | Improved |
| add progressive layer-wise generation (ablation) | H2MM diffusion · ShapeNet | FID: 32.0 -> 28.3 | Improved |
| use part-aware hyperbolic hierarchy instead of Euclidean hierarchy (HGMMSplatting) | 3DGS generation · ShapeNet Car | FID-50K: 11.03 -> 9.89 | Improved |
| use H2MM over GaussianCube for image-to-3D | image-to-3D · Image-to-3D | PSNR: 25.83 -> 27.63 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- GaussianCube — GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling (NeurIPS 2024) · better on 3 of 3 shared results
- DiffSplat — DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation (ICLR 2025) · better on 2 of 2 shared results
- GET3D — GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images (NeurIPS 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.89)
- Large-Vocabulary 3D Diffusion Model with Transformer (ICLR 2024 · similarity 0.88)
- LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion (ICLR 2025 · similarity 0.88)
- Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features (CVPR 2024 · similarity 0.88)
- HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation (CVPR 2024 · similarity 0.87)
- LT3SD: Latent Trees for 3D Scene Diffusion (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
