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.
MonSter++: A Unified Geometric Foundation Model for Stereo and Multi-View Depth Estimation via the Unleashing of Monodepth Priors
| Date | Stars |
|---|---|
| 2026-07-31 | 278 |
| 2026-08-06 | 278 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# 🚀 MonSter++ 🚀 MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priors <a href="https://arxiv.org/abs/2501.08643"><img src="https://img.shields.io/badge/arXiv-2501.08643-b31b1b?logo=arxiv" alt='arxiv'></a> <p align="center"> </p> <h2>🤗 Demo Video：</h2> <div align="center"> <a href="https://www.youtube.com/watch?v=YIhQCuQAKrU"> <img src="Media/demo.png" width="50%" alt="Overview Video"> </a> </div> <p></p> <div align="center"> </div> # 🚀 RT-MonSter++ 🚀 - `[2025/12]` We release the ONNX and TensorRT export and conversion scripts for RT-MonSter++, enabling efficient inference on mobile and edge devices. Further optimizations are planned, including integrating techniques from DepthAnything to further improve efficiency! - <img width="300" height="220" alt="45a82bb73e85fb4a66ade8bd3c441b48" src="https://github.com/user-attachments/assets/c34a5e24-8327-4b61-9e17-66d286e2be2c" /> ## News - `[2025/12]` The most often asked about the issue: ONNX and tensorRT export problems: can be reference to https://github.com/Junda24/MonSter-plusplus/pull/4 - `[2025/9]` We have open-sourced our lightweight real-time model RT-MonSter++ - `[2025/9]` Weights for RT-MonSter++ model released! - `[2025/10]` We have open-sourced our accuracy model MonSter++ - `[2025/10]` Weights for MonSter++ model released! ## ✈️ MonSter++ Model weights (accuracy models) | Model | Link | |:----:|:-------------------------------------------------------------------------------------------------:| | KITTI| [Download 🤗](https://huggingface.co/cjd24/MonSter-plusplus/resolve/main/KITTI_large.pth?download=true) | | ETH3D | [Download 🤗](https://huggingface.co/cjd24/MonSter-plusplus/resolve/main/ETH3D_large.pth?download=true)| |Middlebury | [Download 🤗](https://huggingface.co/cjd24/MonSter-plusplus/resolve/main/Middlebury_large.pth?download=true)| |mix_all | [Download 🤗](https://huggingface.co/cjd24/MonSter-plusplus/resolve/main/Mix_all_large.pth?download=true)| The mix_all model is trained on all the datasets we collect over 2M image pairs, which has the best performance on zero-shot generalization. ## ✈️ RT-MonSter++ Model weights (light weight models) | Model | Link | |:----:|:-------------------------------------------------------------------------------------------------:| | KITTI 2012| [Download 🤗](https://huggingface.co/cjd24/MonSter-plusplus/resolve/main/KITTI_2012.pth?download=true) | | KITTI 2015 | [Download 🤗](https://huggingface.co/cjd24/MonSter-plusplus/resolve/main/KITTI_2015.pth?download=true)| |mix_all | [Download 🤗](https://huggingface.co/cjd24/MonSter-plusplus/resolve/main/Zero_shot.pth?download=true)| The mix_all model is trained on all the datasets we collect over 2M image pairs, which has the best performance on zero-shot generalization. ### 🎬 Dependencies ```Shell pip install torch==2.4.1 torchvision==0.19.1 torchaudio==2.4.1 --index-url https://download.pytorch.org/whl/cu121 pip install tqdm pip install scipy pip install opencv-python pip install scikit-image pip install tensorboard pip install matplotlib pip install timm==0.6.13 pip install mmcv==2.2.0 -f https://download.openmmlab.com/mmcv/dist/cu121/torch2.4/index.html pip install accelerate==1.0.1 pip install gradio_imageslider pip install gradio==4.29.0 pip install "git+https://github.com/facebookresearch/pytorch3d.git" pip install openexr pip install pyexr pip install imath pip install h5py pip install swanlab ``` # Leaderboards 🏆 We obtained the 1st place on the world-wide [KITTI 2012 leaderboard](https://www.cvlibs.net/datasets/kitti/eval_stereo_flow.php?benchmark=stereo) and [KITTI 2015 leaderboard](https://www.cvlibs.net/datasets/kitti/eval_scene_flow.php?benchmark=stereo). 1. [KITTI 2012 leaderboard](https://www.cvlibs.net/
Excerpt of 5,993 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9fd51c69620ea0b3, desc:depth estimation