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.
A curated list of 3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs, inspired by awesome-computer-vision, including papers, codes, and related websites
| Date | Stars |
|---|---|
| 2026-07-24 | 818 |
| 2026-07-25 | 818 |
| 2026-07-28 | 819 |
| 2026-07-30 | 820 |
| 2026-08-06 | 820 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome-Robotics-3D [](https://github.com/sindresorhus/awesome) [](https://GitHub.com/Naereen/StrapDown.js/graphs/commit-activity) [](http://makeapullrequest.com) <a href="" target='_blank'><img src="https://visitor-badge.laobi.icu/badge?page_id=zubairirshad.robotics3d&left_color=gray&right_color=blue"> </a>
<div align="center">
<img src="demo/awesome-robotics-3d.jpg" width="100%">
</div>
## ✨ About
This repo contains a curated list of **3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs**, inspired by [awesome-computer-vision](https://github.com/jbhuang0604/awesome-computer-vision) <br>
#### Please feel free to send me [pull requests](https://github.com/zubair-irshad/Awesome-Robotics-3D/blob/main/how-to-PR.md) or [email](mailto:[email protected]) to add papers!
If you find this repository useful, please consider [citing](#citation) 📝 and STARing ⭐ this list.
Feel free to share this list with others! List curated and maintained by [Zubair Irshad](https://zubairirshad.com). If you have any questions, please get in touch!
:fire: Other relevant survey papers:
* "Neural Fields in Robotics", *arXiv, Oct 2024*. [[Paper](https://arxiv.org/pdf/2410.20220)]
* "When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models", *arXiv, May 2024*. [[Paper](https://arxiv.org/pdf/2405.10255)]
* "3D Gaussian Splatting in Robotics: A Survey", *arXiv, Oct 2024*. [[Paper](https://arxiv.org/pdf/2410.12262)]
* "A Comprehensive Study of 3-D Vision-Based Robot Manipulation", *TCYB 2021*. [[Paper](https://ieeexplore.ieee.org/document/9541299)]
---
## 🏠 Overview
- [Policy Learning](#policy-learning)
- [Pretraining](#pretraining)
- [VLM and LLM](#vlm-and-llm)
- [Representations](#representation)
- [Simulations, Datasets and Benchmarks](#simulations-datasets-and-benchmarks)
- [Citation](#citation)
---
## Policy Learning
* **SAM2Act**: "Integrating Visual Foundation Model with a Memory Architecture for Robotic Manipulation", *ICML 2025*. [[Paper](https://arxiv.org/abs/2501.18564)] [[Webpage](https://sam2act.github.io/)] [[Code](https://github.com/sam2act/SAM2Act)]
* **3D Diffuser Actor**: "Policy diffusion with 3d scene representations", *arXiv Feb 2024*. [[Paper](https://arxiv.org/pdf/2402.10885)] [[Webpage](https://3d-diffuser-actor.github.io/)] [[Code](https://github.com/nickgkan/3d_diffuser_actor)]
* **3D Diffusion Policy**: "Generalizable Visuomotor Policy Learning via Simple 3D Representations", *RSS 2024*. [[Paper](https://arxiv.org/pdf/2403.03954)] [[Webpage](https://arxiv.org/pdf/2403.039545)] [[Code](https://github.com/YanjieZe/3D-Diffusion-Policy)]
* **DNAct**: "Diffusion Guided Multi-Task 3D Policy Learning", *arXiv Mar 2024*. [[Paper](https://arxiv.org/pdf/2403.04115 )] [[Webpage](https://dnact.github.io/)]
* **ManiCM**: "Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation", *arXiv Jun 2024*. [[Paper](https://arxiv.org/pdf/2406.01586)] [[Webpage](https://manicm-fast.github.io/)] [[Code](https://github.com/ManiCM-fast/ManiCM)]
* **HDP**: "Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation", *CVPR 2024*. [[Paper](https://arxiv.org/pdf/2403.03890)] [[Webpage](https://yusufma03.github.io/projects/hdp/)] [[Code](https://github.com/dyson-ai/hdp)]
* **Imagination Policy**: "Using Generative Point Cloud Models for Learning Manipulation Policies", *arXiv Jun 2024*. [[Paper](https://arxiv.org/pdf/2406.11740)] [[Webpage](https://haojhuang.github.io/imagine_page/)]
* **PCWM**: "Point Cloud Models Improve Visual Robustness in Robotic Learners",Excerpt of 26,817 characters
Read on GitHub
Zubair Irshad · @GeorgiaTech @TRI-ML @GT-RIPL · United States
30
6
Beihang University · China
1
1
1
1
Yuxuan Kuang · Carnegie Mellon University
1
1
1
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2120b47c77c5f747, topic:computer-vision, topic:nerf, topic:gaussian-splatting
matched fp:2120b47c77c5f747, topic:llm, topic:foundation-models
matched fp:2120b47c77c5f747, topic:vision-language-model, topic:vlm
matched fp:2120b47c77c5f747, topic:robotics, topic:manipulation, name:robotics