Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling
| Date | Stars |
|---|---|
| 2026-07-24 | 604 |
| 2026-07-25 | 604 |
| 2026-07-28 | 604 |
| 2026-07-30 | 604 |
| 2026-08-08 | 607 |
| 2026-08-16 | 608 |
| 2026-08-19 | 607 |
| 2026-08-21 | 608 |
| 2026-08-27 | 609 |
| 2026-09-12 | 611 |
| 2026-09-20 | 611 |
Today
— stars today
This week
— stars this week
This month
+3 stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<img width="400" alt="image" src="assets/logo_zheng.png">
<!-- <br> -->
</div>
<div align="center">
# Aether: Geometric-Aware Unified World Modeling
</div>
<div align="center">
<a href='https://arxiv.org/abs/2503.18945'><img src='https://img.shields.io/badge/arXiv-2503.18945-red'></a>
<a href='https://aether-world.github.io'><img src='https://img.shields.io/badge/Project-Page-Green'></a>
<a href='https://huggingface.co/AetherWorldModel/AetherV1'><img src='https://img.shields.io/badge/Model-Weights-yellow'></a>
<a href='https://huggingface.co/spaces/AmberHeart/AetherV1'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Demo%20-blue'></a>
</div>
Aether addresses a fundamental challenge in AI: integrating geometric reconstruction with generative modeling
for human-like spatial reasoning. Our framework unifies three core capabilities: (1) 🌏 **4D dynamic reconstruction**,
(2) 🎬 **action-conditioned video prediction**, and (3) 🎯 **goal-conditioned visual planning**. Trained entirely on
synthetic data, Aether achieves strong zero-shot generalization to real-world scenarios.
<div align="center">
<img src="assets/teaser.png" alt="Teaser" width="800"/>
</div>
:partying_face: **NEWS**:
- *Oct.22nd 2025:* Aether won the **Outstanding Paper Award** at the ICCV 2025 RIWM workshop!
- *Jun.26th 2025:* Aether is accepted by ICCV 2025!
- *Jun.3rd 2025:* [DeepVerse](https://github.com/SOTAMak1r/DeepVerse) is released! It is a 4D auto-regressive world model. Check it out!
- *Mar.31st 2025:* The Gradio demo is available! You can deploy locally or experience Aether online on Hugging Face.
- *Mar.28th 2025:* AetherV1 is released! Model checkpoints, paper, website, and inference code are all available.
## :hammer: Installation
Note: We recommend using virtual environments such as [Anaconda](https://www.anaconda.com/).
```console
# clone project
git clone https://github.com/OpenRobotLab/Aether.git
cd Aether
# create conda environment
conda create -n aether python=3.10
conda activate aether
# install dependencies
pip install -r requirements.txt
```
## :rocket: Inference
> ***Warning***: When doing reconstruction, Aether pipeline automatically centers crop the input video if its size does not match 480x720.
Therefore, for evaluation purpose, we have to slide a 480p window both on the spatial and temporal dimensions,
and blend all windows' outputs both spatially and temporally. Examples of video depth and camera pose evaluation can be found at [evaluation/](evaluation/).
### Run inference demo locally
- 4D reconstruction:
```console
python scripts/demo.py --task reconstruction --video ./assets/example_videos/moviegen.mp4
```
- Action-conditioned video prediction:
```console
python scripts/demo.py --task prediction --image ./assets/example_obs/car.png --raymap_action assets/example_raymaps/raymap_forward_right.npy
```
- Goal-conditioned visual planning:
```console
python scripts/demo.py --task planning --image ./assets/example_obs_goal/01_obs.png --goal ./assets/example_obs_goal/01_goal.png
```
Results will be saved in `./outputs/` by default.
### Run inference demo with Gradio
The Gradio demo provides an interactive web-based Aether experience.
```shell
python scripts/demo_gradio.py
```
Our local testing environment is deployed using an A100 GPU with 80GB of memory, and it is set to run on the local port 7860 by default.
### Inference with your own raymap action
Suppose you have a sequence of camera poses, you have to convert it to raymap action trajectories before inference with Aether.
Note that your camera poses should be **within the camera coordinate system of the first frame**.
You can use the `camera_pose_to_raymap` function in [postprocess_utils.py](aether/utils/postprocess_utils.py).
```python
# suppose you have the ground-truth depth values:
disparity = 1. / depth[depth > 0]
dmax = disparity.max()
# otherwise, you Excerpt of 6,701 characters
Read on GitHub
Haoyi Zhu · University of Science and Technology of China · China
12
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c289c16bdc18b0f0, topic:foundation-models, readme:model weights
matched fp:c289c16bdc18b0f0, topic:video-generation
matched fp:c289c16bdc18b0f0, topic:embodied-ai