# sample-imageinpainting-HiFill

**Repository Path**: zyabo/sample-imageinpainting-HiFill

## Basic Information

- **Project Name**: sample-imageinpainting-HiFill
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: BSD-3-Clause
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-12-16
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README


 # Image Inpainting Project based on CVPR 2020 Oral Paper on HiFill
<a href="https://arxiv.org/abs/2005.09704">Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting</a>

Explanation of the model can be found [here](https://github.com/Ascend-Huawei/Ascend-Canada/tree/master/Models/Research_HiFIll_Model)

please cite the paper, if the codes has been used for your research.


```
@misc{yi2020contextual,
    title={Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting},
    author={Zili Yi and Qiang Tang and Shekoofeh Azizi and Daesik Jang and Zhan Xu},
    year={2020},
    eprint={2005.09704},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}
```

<a href="https://www.youtube.com/watch?v=Q7mX5Bstv7U">Youtube video</a>

## Project Diagram

![Diagram_1](imgs/diagram_1.png?raw=true)

## Implementation

* [Implementation on Huawei Ascend 310 AI Processor](./Huawei_Ascend)
* [Implementation on GPU/CPU](./GPU_CPU)

## Experimental results:

![HD](imgs/hd.jpg?raw=true)
![compare](imgs/compare.jpg?raw=true)