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.
About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]
| Date | Stars |
|---|---|
| 2026-07-24 | 891 |
| 2026-07-25 | 891 |
| 2026-07-28 | 891 |
| 2026-07-30 | 891 |
| 2026-08-06 | 891 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<h1 align="center">top CVPR 2025 papers</h1>
<a href="https://github.com/SkalskiP/top-cvpr-2023-papers">2023</a> | <a href="https://github.com/SkalskiP/top-cvpr-2024-papers">2024</a> | <a href="https://github.com/SkalskiP/top-cvpr-2025-papers">2025</a> | <a href="https://github.com/SkalskiP/top-cvpr-2026-papers">2026</a>
</div>
<br>
<div align="center">
<img width="600" src="https://storage.googleapis.com/com-roboflow-marketing/cvpr-2025-posters/IMG_5342_.JPG" />
</div>
## 👋 hello
Computer Vision and Pattern Recognition is a massive conference. In **2025** alone,
**13,008** papers were submitted, and **2,878** were accepted. I created this repository
to help you search for crème de la crème of CVPR publications. If the paper you are
looking for is not on my short list, take a peek at the full
[list](https://cvpr.thecvf.com/Conferences/2025/AcceptedPapers) of accepted papers.
## 🗞️ papers and posters
*🔥 - highlighted papers*
<!--- AUTOGENERATED_PAPERS_LIST -->
<!---
WARNING: DO NOT EDIT THIS LIST MANUALLY. IT IS AUTOMATICALLY GENERATED.
HEAD OVER TO https://github.com/SkalskiP/top-cvpr-2024-papers/blob/master/CONTRIBUTING.md FOR MORE DETAILS ON HOW TO MAKE CHANGES PROPERLY.
-->
### 3d vision
<p align="left">
<a href="https://cvpr.thecvf.com/media/PosterPDFs/CVPR%202025/33969.png?t=1748740040.9726639" title="VGGT: Visual Geometry Grounded Transformer">
<img src="https://storage.googleapis.com/com-roboflow-marketing/cvpr-2025-posters/33969.png" alt="VGGT: Visual Geometry Grounded Transformer" width="400px" align="left" />
</a>
<a href="https://arxiv.org/abs/2503.11651" title="VGGT: Visual Geometry Grounded Transformer">
<strong>🔥 VGGT: Visual Geometry Grounded Transformer</strong>
</a>
<br/>
Jianyuan Wang, Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht, David Novotny
<br/>
[<a href="https://arxiv.org/abs/2503.11651">paper</a>] [<a href="https://github.com/facebookresearch/vggt">code</a>] [<a href="https://youtu.be/7ZYwJEpCUUA">video</a>] [<a href="https://huggingface.co/spaces/facebook/vggt">demo</a>]
<br/>
<strong>Topic:</strong> 3D Vision
<br/>
<strong>Session:</strong> Fri 13 Jun 2 p.m. PDT — 4 p.m. PDT Poster Session 2 #86
</p>
<br/>
<br/>
<p align="left">
<a href="https://cvpr.thecvf.com/media/PosterPDFs/CVPR%202025/34871.png?t=1748708079.0490072" title="MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors">
<img src="https://storage.googleapis.com/com-roboflow-marketing/cvpr-2025-posters/34871.png" alt="MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors" width="400px" align="left" />
</a>
<a href="https://arxiv.org/abs/2412.12392" title="MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors">
<strong>🔥 MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors</strong>
</a>
<br/>
Riku Murai, Eric Dexheimer, Andrew J. Davison
<br/>
[<a href="https://arxiv.org/abs/2412.12392">paper</a>] [<a href="https://github.com/rmurai0610/MASt3R-SLAM">code</a>] [<a href="https://www.youtube.com/watch?v=wozt71NBFTQ">video</a>]
<br/>
<strong>Topic:</strong> 3D Vision
<br/>
<strong>Session:</strong> Sat 14 Jun 3 p.m. PDT — 5 p.m. PDT Poster Session 4 #83
</p>
<br/>
<br/>
<p align="left">
<a href="https://cvpr.thecvf.com/media/PosterPDFs/CVPR%202025/35013.png?t=1748718962.8355792" title="RelationField: Relate Anything in Radiance Fields">
<img src="https://storage.googleapis.com/com-roboflow-marketing/cvpr-2025-posters/35013.png" alt="RelationField: Relate Anything in Radiance Fields" width="400px" align="left" />
</a>
<a href="https://arxiv.org/abs/2412.13652" title="RelationField: Relate Anything in Radiance Fields">
<strong>RelationField: Relate Anything in Radiance Fields</strong>
</a>Excerpt of 36,958 characters
Read on GitHub
Piotr Skalski · @roboflow
32
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:7967129c5552464b, topic:computer-vision, topic:object-detection, topic:image-segmentation
matched fp:7967129c5552464b, topic:multimodal, topic:vision-language-model