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.
[TPAMI 2026] 3D and 4D World Modeling: A Survey
| Date | Stars |
|---|---|
| 2026-07-30 | 954 |
| 2026-08-09 | 960 |
| 2026-08-17 | 965 |
| 2026-08-18 | 966 |
| 2026-08-21 | 967 |
| 2026-08-25 | 968 |
| 2026-08-26 | 970 |
| 2026-08-27 | 971 |
| 2026-08-28 | 973 |
| 2026-08-30 | 974 |
| 2026-08-31 | 976 |
| 2026-09-01 | 977 |
| 2026-09-02 | 979 |
| 2026-09-06 | 980 |
| 2026-09-07 | 982 |
| 2026-09-09 | 983 |
| 2026-09-14 | 983 |
| 2026-09-15 | 984 |
| 2026-09-16 | 985 |
| 2026-09-20 | 986 |
| 2026-09-21 | 987 |
| 2026-09-22 | 988 |
| 2026-09-25 | 989 |
| 2026-09-27 | 990 |
| 2026-09-28 | 991 |
| 2026-09-29 | 992 |
| 2026-09-30 | 993 |
| 2026-10-02 | 993 |
| 2026-10-03 | 992 |
| 2026-10-07 | 993 |
| 2026-10-08 | 996 |
| 2026-10-09 | 995 |
| 2026-10-10 | 996 |
| 2026-10-12 | 997 |
| 2026-10-15 | 1000 |
| 2026-10-16 | 1002 |
| 2026-10-17 | 1003 |
| 2026-10-18 | 1006 |
| 2026-10-19 | 1010 |
| 2026-10-20 | 1012 |
| 2026-10-21 | 1012 |
| 2026-10-22 | 1013 |
| 2026-10-24 | 1015 |
| 2026-10-25 | 1016 |
| 2026-10-26 | 1017 |
| 2026-10-27 | 1019 |
| 2026-10-30 | 1020 |
| 2026-11-02 | 1022 |
| 2026-11-03 | 1023 |
| 2026-11-04 | 1024 |
Today
+1 stars today
This week
+5 stars this week
This month
+32 stars this month
Momentum
9.0
growth rate 0.49%/day
[](https://github.com/sindresorhus/awesome)
[](https://arxiv.org/abs/2509.07996)
[](https://github.com/worldbench/awesome-3d-4d-world-models/pulls)
# :sunglasses: Awesome 3D and 4D World Models
| <img width="100%" src="docs/figures/teaser.png"> |
|:-:|
This survey reviews state-of-the-art **3D and 4D world models** - systems that learn, predict, and simulate the geometry and dynamics of real environments from multi-modal signals.
We unify terminology, scope, and evaluations, and organize the space into three complementary paradigms by representation:
| | |
|:-:|:-|
| <img width="240px" src="docs/figures/icon_videogen.png"> | Learn generative or predictive models from sequential video streams with geometric and temporal constraints. VideoGen focuses on long-horizon consistency, controllability, and scene-level generation, enabling agents to imagine or forecast plausible video rollouts. |
| <img width="240px" src="docs/figures/icon_occgen.png"> | Model 3D/4D occupancy grids that encode geometry and semantics in voxel space. OccGen provides a physics-consistent scaffold for robust perception, forecasting, and simulation, bridging low-level sensor data and high-level reasoning. |
| <img width="240px" src="docs/figures/icon_lidargen.png"> | Leverage point cloud sequences from LiDAR sensors to generate or predict geometry-grounded scenes. LiDARGen emphasizes high-fidelity 3D structure, robustness to environment changes, and applications in safety-critical domains such as autonomous driving. |
| | |
For more details, kindly refer to our [paper](https://huggingface.co/papers/2509.07996) and [project page](https://worldbench.github.io/survey). :rocket:
### :books: Citation
If you find this work helpful for your research, please kindly consider citing our papers:
```bib
@article{survey_3d_4d_world_models,
title = {{3D} and {4D} World Modeling: A Survey},
author = {Lingdong Kong and Yu Yang and Jianbiao Mei and Youquan Liu and Ao Liang and Dekai Zhu and Dongyue Lu and Wei Yin and Xiaotao Hu and Mingkai Jia and Junyuan Deng and Kaiwen Zhang and Yang Wu and Tianyi Yan and Shenyuan Gao and Song Wang and Linfeng Li and Liang Pan and Yong Liu and Jianke Zhu and Wei Tsang Ooi and Steven C. H. Hoi and Ziwei Liu},
journal = {arXiv preprint arXiv:2509.07996},
year = {2025}
}
```
```bibtex
@inproceedings{worldlens,
title = {{WorldLens}: Full-Spectrum Evaluations of Driving World Models in Real World},
author = {Ao Liang and Lingdong Kong and Tianyi Yan and Hongsi Liu and Wesley Yang and Ziqi Huang and Wei Yin and Jialong Zuo and Yixuan Hu and Dekai Zhu and Dongyue Lu and Youquan Liu and Guangfeng Jiang and Linfeng Li and Xiangtai Li and Long Zhuo and Lai Xing Ng and Benoit R. Cottereau and Changxin Gao and Liang Pan and Wei Tsang Ooi and Ziwei Liu},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
pages = {36385-36399},
year = {2026}
}
```
### Table of Contents
- [Background](#background)
- [What Are Native 3D Representations?](#what-are-native-3d-representations)
- [What Are World Models in 3D and 4D?](#what-are-world-models-in-3d-and-4d)
- [1. Benchmarks \& Datasets](#1-benchmarks--datasets)
- [Benchmarks](#benchmarks)
- [Workshops](#workshops)
- [Datasets](#datasets)
- [2. World Modeling from Video Generation](#2-world-modeling-from-video-generation)
- [Data Engines](#one-data-engines)
- [Action Interpreters](#two-action-interpreters)
- [Neural Simulators](#three-neural-simExcerpt of 180,007 characters
Read on GitHub
Lingdong Kong · National University of Singapore · Singapore
90
14
6
2
2
1
1
1
Zhening Huang
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3b6052d93b565514, topic:embodied-ai, topic:autonomous-driving, readme:autonomous driving
matched fp:3b6052d93b565514, topic:video-generation, readme:video generation
matched fp:3b6052d93b565514, topic:awesome-list