DIS-inference

Inference implementation of Dichotomous Image Segmentation

Highly Accurate Dichotomous Image Segmentation (ECCV 2022)

Xuebin Qin, Hang Dai, Xiaobin Hu, Deng-Ping Fan*, Ling Shao, Luc Van Gool.

Project Page, Arxiv, **中文 **.

Origin	DIS

Table of Contents

• Installation
• Usage
• License
• Reference

Installation

pip install dis-inference

Usage

CLI

command: dis-inference

arguments:

• --silent(optional) : Whether to print verbose.
• Source image(mandatory) : Source image path.

> dis-inference Lenna.png
Output saved as `Lenna_dis.png`
> dis-inference --silent Lenna.png

Python

from dis_inference import inference

# 1. Inference with path
output = inference('Lenna.png')
cv2.imwrite('Lenna_dis.png', output)

# 2. Inference cv2 image
image = cv2.imread('Lenna.png')
output = inference(image)
cv2.imwrite('Lenna_dis.png', output)

# 3. Inference cv2 image with save parameter
image = cv2.imread('Lenna.png')
output = inference(image, save=True, output='Lenna_dis.png')

# 4. With save parameter
image = inference('Lenna.png', save=True)

License

dis-inference is distributed under the terms of the Apache-2.0 license.

Reference

https://github.com/xuebinqin/DIS

Citation

@InProceedings{qin2022,
      author={Xuebin Qin and Hang Dai and Xiaobin Hu and Deng-Ping Fan and Ling Shao and Luc Van Gool},
      title={Highly Accurate Dichotomous Image Segmentation},
      booktitle={ECCV},
      year={2022}
}