https://github.com/aim-uofa/adelaidepth

This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.
https://github.com/aim-uofa/adelaidepth

3d-scene-shape depth-prediction

Last synced: 4 days ago
JSON representation

This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.

• Host: GitHub
• URL: https://github.com/aim-uofa/adelaidepth
• Owner: aim-uofa
• License: cc0-1.0
• Created: 2020-11-19T06:28:43.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2023-11-10T08:14:10.000Z (about 1 year ago)
• Last Synced: 2024-12-22T23:03:10.718Z (11 days ago)
• Topics: 3d-scene-shape, depth-prediction
• Language: Python
• Homepage:
• Size: 44.7 MB
• Stars: 1,071
• Watchers: 34
• Forks: 145
• Open Issues: 48
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# AdelaiDepth

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1rDLZBtiUgsFJrrL-xOgTVWxj6PMK9swq?usp=sharing)

AdelaiDepth is an open source toolbox for monocular depth prediction. Relevant work from our group is open-sourced here.

AdelaiDepth contains the following algorithms:

* 3D Scene Shape (Best Paper Finalist): [Code](https://github.com/aim-uofa/AdelaiDepth/tree/main/LeReS), [Learning to Recover 3D Scene Shape from a Single Image](https://arxiv.org/abs/2012.09365)

* DiverseDepth: [Code](https://github.com/YvanYin/DiverseDepth), [Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction](https://arxiv.org/abs/2103.04216), [DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data](https://arxiv.org/abs/2002.00569)

* Virtual Normal: [Code](https://github.com/YvanYin/VNL_Monocular_Depth_Prediction),  [Enforcing geometric constraints of virtual normal for depth prediction](https://arxiv.org/abs/1907.12209)

* Depth Estimation Using Deep Convolutional Neural Fields: [Code](https://bitbucket.org/fayao/dcnf-fcsp/src/master/), [Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields, TPAMI'16, CVPR'15](https://arxiv.org/abs/1502.07411)

## News:

* [May. 31, 2022] Training code and data of LeReS project have been released.

* [Feb. 13, 2022] Training code and data of DiverseDepth project have been released.

* [Jun. 13, 2021] Our "Learning to Recover 3D Scene Shape from a Single Image" work is one of the CVPR'21 Best Paper Finalists.

* [Jun. 6, 2021] We have made the training data of DiverseDepth available.

## Results and Dataset Examples:

1. 3D Scene Shape

  

 You may want to check [this video](http://www.youtube.com/watch?v=UuT5_GK_TWk) which provides a very brief introduction to the work:

  

    RGB

     Depth

     Point Cloud

  

  

      

    

    

  

 

![Depth](./examples/depth.png)

2. DiverseDepth

* Results examples：

![Depth](./examples/diverse_depth.jpg)

* DiverseDepth dataset examples：

![DiverseDepth dataset](./examples/diversedepth_dataset_examples.png)

## BibTeX

```BibTeX

@article{yin2022towards,

  title={Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image},

  author={Yin, Wei and Zhang, Jianming and Wang, Oliver and Niklaus, Simon and Chen, Simon and Liu, Yifan and Shen, Chunhua},

  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},

  year={2022}

}

@inproceedings{Yin2019enforcing,

  title     = {Enforcing geometric constraints of virtual normal for depth prediction},

  author    = {Yin, Wei and Liu, Yifan and Shen, Chunhua and Yan, Youliang},

  booktitle = {The IEEE International Conference on Computer Vision (ICCV)},

  year      = {2019}

}

@inproceedings{Wei2021CVPR,

  title     =  {Learning to Recover 3D Scene Shape from a Single Image},

  author    =  {Wei Yin and Jianming Zhang and Oliver Wang and Simon Niklaus and Long Mai and Simon Chen and Chunhua Shen},

  booktitle =  {Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (CVPR)},

  year      =  {2021}

}

@article{yin2021virtual,

  title   = {Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction},

  author  = {Yin, Wei and Liu, Yifan and Shen, Chunhua},

  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},

  year    = {2021}

}

```

## License

The *3D Scene Shape* code is under a non-commercial license from *Adobe Research*. See the [LICENSE file](LeReS/LICENSE) for details.

Other depth prediction projects are licensed under the 2-clause BSD License for non-commercial use -- see the [LICENSE file](LICENSE) for details. For commercial use, please contact [Chunhua Shen](https://cshen.github.io).