adobe-research / EntitySeg-Dataset

Adobe-EntitySeg dataset

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Adobe's Entity Segmentation dataset

image

This repository provides mask annotations and image URLs for the EntitySeg dataset as described in the ICCV2023 paper:

  High-Quality Entity Segmentation

   Lu Qi, Jason Kuen, Tiancheng Shen, Weidong Guo, Jiuxiang Gu, Jiaya Jia, Zhe Lin, Ming-Hsuan Yang

Download annotation files

The dataset annotations can be downloaded here.

Download images

Images can be downloaded through the image source entries and/or URLs that we provide in url.json. Alternatively, you may obtain the images which are pre-downloaded based on url.json from an independent source. Please note that we do not own the copyright of the images. It is solely your responsibility to check the original licenses of the images before using them. Any use of the images are at your own discretion and risk.

Supplementary repo for code and models

Supplementary repo

Citation

Please cite our ICCV2023 paper if you use the EntitySeg dataset in your work.

@InProceedings{Qi_2023_EntitySeg,
    author    = {Qi, Lu and Kuen, Jason and Shen, Tiancheng and Gu, Jiuxiang and Guo, Weidong and Jia, Jiaya and Lin, Zhe and Yang, Ming-Hsuan},
    title     = {High-Quality Entity Segmentation},
    booktitle = {International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2023},
}

License

This dataset is released under Adobe Research License. The license prohibits commercial use and allows for non-commercial research use.

About

Adobe-EntitySeg dataset

License:Other