Loopy-SLAM

KO | EN

gitlite — search

#python #hacktoberfest #react #typescript #llm #android #rust #linux #nodejs #macos #java #windows #awesome #pytorch

(★ 165)

No description available.

파일 탐색기

최종 버전 다운로드 (.zip)

- - office0.yaml
  - office1.yaml
  - office2.yaml
  - office3.yaml
  - office4.yaml
  - replica.yaml
  - room0.yaml
  - room1.yaml
  - room2.yaml
- - scannet.yaml
  - scene0000.yaml
  - scene0025.yaml
  - scene0054.yaml
  - scene0059.yaml
  - scene0062.yaml
  - scene0103.yaml
  - scene0106.yaml
  - scene0126.yaml
  - scene0169.yaml
  - scene0181.yaml
  - scene0207.yaml
  - scene0233.yaml
  - scene0465.yaml
- - freiburg1_desk.yaml
  - freiburg1_desk2.yaml
  - freiburg1_room.yaml
  - freiburg2_xyz.yaml
  - freiburg3_office.yaml
  - tum.yaml
- point_slam.yaml
- architecture.jpg
- scene54.gif
- coarse.pt
- color.pt
- middle_fine.pt
- download_apartment.sh
- download_cull_replica_mesh.sh
- download_replica.sh
- download_tum.sh
- - __init__.py
  - config.py
- - cull_mesh.py
  - eval_ate.py
  - eval_images.py
  - eval_recon.py
  - get_mesh_tsdf_fusion.py
  - get_mesh_video.py
  - get_mesh_video_old.py
  - viz.py
  - viz_old.py
- - datasets.py
  - Logger.py
  - Renderer.py
  - visual_odometer.py
  - Visualizer.py
- __init__.py
- common.py
- config.py
- Mapper.py
- neural_point.py
- Point_SLAM.py
- Tracker.py
.gitignore
env.yaml
LICENSE
README.md
run.py

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<h1 align="center">Loopy-SLAM: Dense Neural SLAM with Loop Closures</h1>
  <h1 align="center">[CVPR 2024]</h1>
  <p align="center">
    <a href="https://github.com/notchla"><strong>Lorenzo Liso*</strong></a>
    .
    <a href="https://eriksandstroem.github.io/"><strong>Erik Sandström*</strong></a>
    ·
    <a href="https://vladimiryugay.github.io/"><strong>Vladimir Yugay</strong></a>
    ·
    <a href="https://vision.ee.ethz.ch/people-details.OTAyMzM=.TGlzdC8zMjcxLC0xOTcxNDY1MTc4.html"><strong>Luc Van Gool</strong></a>
    ·
    <a href="http://people.inf.ethz.ch/moswald/"><strong>Martin R. Oswald</strong></a>
  </p>
  <p align="center"><strong>(* Equal Contribution)</strong></p>
  <h3 align="center"><a href="http://arxiv.org/abs/2402.09944">Paper</a> | <a href="https://notchla.github.io/Loopy-SLAM">Project Page</a> 
  <div align="center"></div>
</p>

<p align="center">
  <a href="">
    <img src="./media/scene54.gif" alt="Logo" width="80%">
  </a>
</p>
<p align="center">
Loopy-SLAM produces accurate dense geometry and camera tracking on large-scale indoor scenes.

<p align="center">
  <a href="">
    <img src="./media/architecture.jpg" alt="Logo" width="100%">
  </a>
</p>
<p align="center">
Loopy-SLAM Architecture.
</p>

<details open="open" style='padding: 10px; border-radius:5px 30px 30px 5px; border-style: solid; border-width: 1px;'>
  <summary>Table of Contents</summary>
  <ol>
    <li>
      <a href="#installation">Installation</a>
    </li>
    <li>
      <a href="#run">Run</a>
    </li>
    <li>
      <a href="#evaluation">Evaluation</a>
    </li>
    <li>
      <a href="#acknowledgement">Acknowledgement</a>
    </li>
    <li>
      <a href="#citation">Citation</a>
    </li>
    <li>
      <a href="#contact">Contact</a>
    </li>
  </ol>
</details>

## Installation

First you have to make sure that you have all dependencies in place.
The simplest way to do so is to use [anaconda](https://www.anaconda.com/).

If you are running Loopy-SLAM on a cluster GPU without a display, we recommend installing the headless version of Open3D which is required to evaluate the depth L1 metric of the reconstructed mesh. This requires compiling Open3D from scratch. The code is tested on Open3D 15.1 and 16.0. If compiling Open3D from scratch, remove the Open3D dependency from the `env.yaml` file.

You can create an anaconda environment called `loopy-slam`.
```bash
conda env create -f env.yaml
conda activate loopy-slam
```

For evaluating the F-score, download and install [this](https://github.com/eriksandstroem/evaluate_3d_reconstruction_lib) library using pip. 
```bash
git clone https://github.com/tfy14esa/evaluate_3d_reconstruction_lib.git
cd evaluate_3d_reconstruction_lib
pip install .
```

To install the bag of words place recognition library, please follow the instructions [here](https://github.com/notchla/PyDBoW3).

## Data Download

### Replica
Download the data as below and the data is saved into the `./datasets/Replica` folder. Note that the Replica data is generated by the authors of iMAP (but hosted by the authors of NICE-SLAM). Please cite iMAP if you use the data.
```bash
bash scripts/download_replica.sh
```
To be able to evaluate the reconstruction error, download the ground truth Replica meshes where unseen region have been culled.

```bash
bash scripts/download_cull_replica_mesh.sh
```

### TUM-RGBD
```bash
bash scripts/download_tum.sh
```
DATAROOT is `./datasets` by default. Please change the `input_folder` path in the scene specific config files if stored somewhere else on your machine.

### ScanNet
Please follow the data downloading procedure on the [ScanNet](http://www.scan-net.org/) website, and extract color/depth frames from the `.sens` file using this [code](https://github.com/ScanNet/ScanNet/blob/master/SensReader/python/reader.py).

<details>
  <summary>[Directory structure of ScanNet (click to expand)]</summary>
  
  DATAROOT is `./datasets` by default. If a sequence (`sceneXXXX_XX`) is stored in other places, please change the `input_folder` path in the config file or in the command line.

```
  DATAROOT
  └── scannet
        └── scene0000_00
            └── frames
                ├── color
                │   ├── 0.jpg
                │   ├── 1.jpg
                │   ├── ...
                │   └── ...
                ├── depth
                │   ├── 0.png
                │   ├── 1.png
                │   ├── ...
                │   └── ...
                ├── intrinsic
                └── pose
                    ├── 0.txt
                    ├── 1.txt
                    ├── ...
                    └── ...
```
</details>

We use the following sequences: 
```
scene0000_00
scene0025_02
scene0059_00
scene0062_00
scene0103_00
scene0106_00
scene0126_00
scene0169_00
scene0181_00
scene0207_00
```

## Run
For running Loopy-SLAM, we recommend using [weights and biases](https://wandb.ai/) for the logging. This can be turned on by setting the `wandb` flag to True in the `configs/point_slam.yaml` file. Also make sure to specify the path `wandb_folder`. If you don't have a wandb account, first create one. Each scene has a config folder, where the `input_folder` and `output` paths need to be specified. Below, we show some example run commands for one scene from each dataset. If you use a batch processing system (e.g [SLURM](https://slurm.schedmd.com/documentation.html)), you might find our `repro.sh` script useful.

### Replica
To run Loopy-SLAM on the `room0` scene, run the following command. 
```bash
python run.py configs/Replica/room0.yaml
```
After reconstruction, the trajectory error will be evaluated and so will the mesh accuracy along with the rendering metrics.

### TUM-RGBD
To run Loopy-SLAM on the `freiburg1_desk` scene, run the following command. 
```bash
python run.py configs/TUM_RGBD/freiburg1_desk.yaml
```
After reconstruction, the trajectory error will be evaluated automatically.

### ScanNet

To run Loopy-SLAM on the `scene0000_00` scene, run the following command. 
```bash
python run.py configs/ScanNet/scene0000_00.yaml
```
After reconstruction, the trajectory error will be evaluated automatically.

## Acknowledgement
Our codebase is based on [Point-SLAM](https://github.com/eriksandstroem/Point-SLAM).

## Reproducibility
There may be minor differences between the released codebase and the results reported in the paper. Further, we note that the GPU hardware has an influence, despite running the same seed and conda environment.

## Citation

If you find our code or paper useful, please cite
```bibtex
@inproceedings{liso2024loopy,
  title={Loopy-slam: Dense neural slam with loop closures},
  author={Liso, Lorenzo and Sandstr{\"o}m, Erik and Yugay, Vladimir and Van Gool, Luc and Oswald, Martin R},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={20363--20373},
  year={2024}
}
```
## Contact
Contact [Erik Sandström](mailto:erik.sandstrm@gmail.com) for questions, comments and reporting bugs.

Loopy-SLAM

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Loopy-SLAM

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README