Need help with DFNet?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

175 Stars 39 Forks Other 13 Commits 0 Opened issues


Deep Fusion Network for Image Completion - ACMMM 2019

Services available


Need anything else?

Contributors list

# 189,721
Deep le...
13 commits

Deep Fusion Network for Image completion


Deep image completion usually fails to harmonically blend the restored image into existing content, especially in the boundary area. And it often fails to complete complex structures.

We first introduce Fusion Block for generating a flexible alpha composition map to combine known and unknown regions. It builds a bridge for structural and texture information, so that information in known region can be naturally propagated into completion area. With this technology, the completion results will have smooth transition near the boundary of completion area.

Furthermore, the architecture of fusion block enable us to apply multi-scale constraints. Multi-scale constrains improves the performance of DFNet a lot on structure consistency.

Moreover, it is easy to apply this fusion block and multi-scale constrains to other existing deep image completion models. A fusion block feed with feature maps and input image, will give you a completion result in the same resolution as given feature maps.

More detail can be found in our paper

The illustration of a fusion block:

Examples of corresponding images:

If you find this code useful for your research, please cite:

 author = {Hong, Xin and Xiong, Pengfei and Ji, Renhe and Fan, Haoqiang},
 title = {Deep Fusion Network for Image Completion},
 booktitle = {Proceedings of the 27th ACM International Conference on Multimedia},
 series = {MM '19},
 year = {2019},
 isbn = {978-1-4503-6889-6},
 location = {Nice, France},
 pages = {2033--2042},
 numpages = {10},
 url = {},
 doi = {10.1145/3343031.3351002},
 acmid = {3351002},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {alpha composition, deep fusion network, fusion block, image completion, inpainting},


  • Python 3
  • PyTorch 1.0
  • OpenCV


Clone this repo:

git clone
cd DFNet

Download pre-trained model from Google Drive and put them into


Testing with Places2 model

There are already some sample images in the

python --model model/model_places2.pth --img samples/places2/img --mask samples/places2/mask --output output/places2 --merge

Testing with CelebA model

There are already some sample images in the

python --model model/model_celeba.pth --img samples/celeba/img --mask samples/celeba/mask --output output/celeba --merge


Please refer to: It is building in progress but looks good so far.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.