Add link to paper page

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -2,14 +2,14 @@
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">
@@ -22,13 +22,13 @@ tags:
22
 
23
  School of Software, Tsinghua University &nbsp;·&nbsp; <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
  ![Four generated 4DGS worlds rendered at different timesteps and viewpoints with depth and normals](https://weiqi-zhang.github.io/AEON/static/img/teaser.webp)
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 &nbsp;·&nbsp; <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
  ![Four generated 4DGS worlds rendered at different timesteps and viewpoints with depth and normals](https://weiqi-zhang.github.io/AEON/static/img/teaser.webp)
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.