Add link to paper page
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -2,14 +2,14 @@
|
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
pipeline_tag: text-to-3d
|
| 4 |
tags:
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
---
|
| 14 |
|
| 15 |
<div align="center">
|
|
@@ -22,13 +22,13 @@ tags:
|
|
| 22 |
|
| 23 |
School of Software, Tsinghua University · <sup>†</sup> Corresponding authors
|
| 24 |
|
| 25 |
-
[**Project Page**](https://weiqi-zhang.github.io/AEON/) | [**Code**](https://github.com/weiqi-zhang/AEON)
|
| 26 |
|
| 27 |
</div>
|
| 28 |
|
| 29 |

|
| 30 |
|
| 31 |
-
AEON is a generative world model that unifies video-based and 3D-based world models. It works in the latent space
|
| 32 |
of a pretrained video diffusion model and produces an explicit **4D Gaussian Splatting (4DGS)** world together with
|
| 33 |
its camera trajectory. The 4DGS world can be rendered in real time at any timestep and from new viewpoints, and it
|
| 34 |
can be edited or used for simulation.
|
|
@@ -154,4 +154,4 @@ licensed for non-commercial research only, such as DynamicReplica and Panda-70M.
|
|
| 154 |
The AEON inference code is released under the [MIT License](https://github.com/weiqi-zhang/AEON/blob/main/LICENSE).
|
| 155 |
The third-party code it includes keeps its original licenses, listed in
|
| 156 |
[THIRD_PARTY_NOTICES.md](https://github.com/weiqi-zhang/AEON/blob/main/THIRD_PARTY_NOTICES.md). The Wan2.1 models
|
| 157 |
-
are distributed by their authors under the Apache-2.0 license.
|
|
|
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
pipeline_tag: text-to-3d
|
| 4 |
tags:
|
| 5 |
+
- 4d-generation
|
| 6 |
+
- gaussian-splatting
|
| 7 |
+
- 4d-gaussian-splatting
|
| 8 |
+
- world-model
|
| 9 |
+
- video-diffusion
|
| 10 |
+
- image-to-3d
|
| 11 |
+
- wan2.1
|
| 12 |
+
- neurips-2026
|
| 13 |
---
|
| 14 |
|
| 15 |
<div align="center">
|
|
|
|
| 22 |
|
| 23 |
School of Software, Tsinghua University · <sup>†</sup> Corresponding authors
|
| 24 |
|
| 25 |
+
[**Paper**](https://huggingface.co/papers/2610.28631) | [**Project Page**](https://weiqi-zhang.github.io/AEON/) | [**Code**](https://github.com/weiqi-zhang/AEON)
|
| 26 |
|
| 27 |
</div>
|
| 28 |
|
| 29 |

|
| 30 |
|
| 31 |
+
AEON ([paper](https://huggingface.co/papers/2610.28631)) is a generative world model that unifies video-based and 3D-based world models. It works in the latent space
|
| 32 |
of a pretrained video diffusion model and produces an explicit **4D Gaussian Splatting (4DGS)** world together with
|
| 33 |
its camera trajectory. The 4DGS world can be rendered in real time at any timestep and from new viewpoints, and it
|
| 34 |
can be edited or used for simulation.
|
|
|
|
| 154 |
The AEON inference code is released under the [MIT License](https://github.com/weiqi-zhang/AEON/blob/main/LICENSE).
|
| 155 |
The third-party code it includes keeps its original licenses, listed in
|
| 156 |
[THIRD_PARTY_NOTICES.md](https://github.com/weiqi-zhang/AEON/blob/main/THIRD_PARTY_NOTICES.md). The Wan2.1 models
|
| 157 |
+
are distributed by their authors under the Apache-2.0 license.
|