Skip to content

Latest commit

 

History

History
51 lines (37 loc) · 2.27 KB

README.md

File metadata and controls

51 lines (37 loc) · 2.27 KB
Raw

Context Encoders: Feature Learning by Inpainting

Accepted at CVPR 2016
Project Website

If you find Context-Encoder useful in your research, please cite:

@inproceedings{pathakCVPR16context,
    Author = {Pathak, Deepak and Kr\"ahenb\"uhl, Philipp and Donahue, Jeff and Darrell, Trevor and Efros, Alexei},
    Title = {Context Encoders: Feature Learning by Inpainting},
    Booktitle = {Computer Vision and Pattern Recognition ({CVPR})},
    Year = {2016}
}

Contents

  1. Semantic Inpainting Demo
  2. Features Caffemodel

1) Semantic Inpainting Demo

Inpainting using context encoder trained jointly with reconstruction and adversarial loss. Currently, I have only released the demo for the center region inpainting only and will release the arbitrary region semantic inpainting models soon.

  1. Install Torch: http://torch.ch/docs/getting-started.html#_

  2. Clone the repository

git clone https://github.com/pathak22/context-encoder.git
  1. Demo
cd context-encoder
bash ./models/scripts/download_inpaintCenter_models.sh
# This will populate the `./models/` folder with trained models.

net=models/inpaintCenter/paris_inpaintCenter.t7 name=paris_result imDir=images/paris overlapPred=4 manualSeed=222 batchSize=21 gpu=1 th demo.lua
net=models/inpaintCenter/imagenet_inpaintCenter.t7 name=imagenet_result imDir=images/imagenet overlapPred=0 manualSeed=222 batchSize=21 gpu=1 th demo.lua
net=models/inpaintCenter/paris_inpaintCenter.t7 name=ucberkeley_result imDir=images/ucberkeley overlapPred=4 manualSeed=222 batchSize=4 gpu=1 th demo.lua
# Note: If you are running on cpu, use gpu=0
# Note: samples given in ./images/* are held-out images

Sample results on held-out images:

teaser

2) Features Caffemodel

Features for context encoder trained with reconstruction loss.