Home

Awesome

Visual Motif Removal

Source code for the <a href="https://arxiv.org/abs/1904.02756" target="_blank">paper</a> Blind Visual Motif Removal from a Single Image.

<p align="center" style= "cursor: text;"> <a href="###" style= "cursor: text;"><img style= "cursor: text;" src="http://www.pxcm.org/motif/arch_diagram.png"></a> </p>

Prerequisites

A pre-trained semi-transparent emojis removal model is available by running the script: demo / run_demo.py.

Training

Start a training session, by run the file train / train_main.py.<br> Different training configurations are placed at the top.

Paths configurations

Network configurations

Testing

The utils / visualize_utils.py script may assist in order to run a trained network on different images. The root_path and train_tag from above should be defined on top.

Datasets

Images <br> The data_prep / coco_download.py script might be helpful to download a collection of images from <a href="http://cocodataset.org/#home" target="_blank">Microsoft COCO dataset</a>.<br>

Text Motifs <br> The visual Motifs may be generated from a text file. examples of the text format are found at data / text folder or use the split_text.py script on a row text file.

Create new Dataset <br> To create a training data use the file utils / cache_utils.py. In there you will define the dataset configurations: