Duplicate from infinith/UltraShape
Browse filesCo-authored-by: thj2333 <infinith@users.noreply.huggingface.co>
- .gitattributes +35 -0
- README.md +42 -0
- ultrashape_v1.pt +3 -0
- vae/vae_step=15000.ckpt +3 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- tencent/Hunyuan3D-2.1
|
| 5 |
+
pipeline_tag: image-to-3d
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+

|
| 9 |
+
|
| 10 |
+
<h1>UltraShape 1.0 Refine Model</h1>
|
| 11 |
+
|
| 12 |
+
<a href="https://arxiv.org/pdf/2512.21185"><img src="https://img.shields.io/badge/arXiv-2512.21185-b31b1b.svg?style=flat-square" alt="arXiv"></a>
|
| 13 |
+
<a href="https://pku-yuangroup.github.io/UltraShape-1.0/"><img src="https://img.shields.io/badge/Project-Page-blue?style=flat-square" alt="Project Page"></a>
|
| 14 |
+
<a href="https://huggingface.co/infinith/UltraShape"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-yellow?style=flat-square" alt="HuggingFace Models"></a>
|
| 15 |
+
<a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg?style=flat-square" alt="License"></a>
|
| 16 |
+
|
| 17 |
+
In this report, we introduce **UltraShape 1.0**, a scalable 3D diffusion framework for high-fidelity 3D geometry generation. The proposed approach adopts a **two-stage generation pipeline**: a coarse global structure is first synthesized and then refined to produce detailed, high-quality geometry.
|
| 18 |
+
|
| 19 |
+
To support reliable 3D generation, we develop a comprehensive data processing pipeline that includes a novel **watertight processing method** and **high-quality data filtering**. This pipeline improves the geometric quality of publicly available 3D datasets by removing low-quality samples, filling holes, and thickening thin structures, while preserving fine-grained geometric details.
|
| 20 |
+
|
| 21 |
+
To enable fine-grained geometry refinement, we decouple spatial localization from geometric detail synthesis in the diffusion process. We achieve this by performing **voxel-based refinement** at fixed spatial locations, where voxel queries derived from coarse geometry provide explicit positional anchors encoded via **RoPE**, allowing the diffusion model to focus on synthesizing local geometric details within a reduced, structured solution space.
|
| 22 |
+
|
| 23 |
+
Extensive evaluations demonstrate that UltraShape 1.0 performs competitively with existing open-source methods in both data processing quality and geometry generation.
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
## 🔗 BibTeX
|
| 27 |
+
|
| 28 |
+
If you found this repository helpful, please cite our report:
|
| 29 |
+
```bibtex
|
| 30 |
+
@article{jia2025ultrashape,
|
| 31 |
+
title={UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement},
|
| 32 |
+
author={Jia, Tanghui and Yan, Dongyu and Hao, Dehao and Li, Yang and Zhang, Kaiyi and He, Xianyi and Li, Lanjiong and Chen, Jinnan and Jiang, Lutao and Yin, Qishen and Quan, Long and Chen, Ying-Cong and Yuan, Li},
|
| 33 |
+
journal={arxiv preprint arXiv:2512.21185},
|
| 34 |
+
year={2025}
|
| 35 |
+
}
|
| 36 |
+
```
|
| 37 |
+
|
| 38 |
+
## Acknowledgements
|
| 39 |
+
|
| 40 |
+
We would like to thank the contributors to
|
| 41 |
+
the [Hunyuan3D-2.1](https://github.com/Tencent-Hunyuan/Hunyuan3D-2.1), [Lattice](https://lattice3d.github.io/), [Cubvh](https://github.com/ashawkey/cubvh)
|
| 42 |
+
and [HuggingFace](https://huggingface.co) repositories, for their research and exploration.
|
ultrashape_v1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c96ae010c4169597fd0006dcb08056bf6104a1fca249b10fed7ddded324c3f0f
|
| 3 |
+
size 7366231254
|
vae/vae_step=15000.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:167d6afa1f0f0c6ffbb2755af8d2ba85248076e1c936d275d0aee8d2636ebd12
|
| 3 |
+
size 655653780
|