ku-cvlab/instaformer

Official repository for InstaFormer: Instance-aware Image-to-Image Translation with Transformer (CVPR 2022)

Instance-aware Image-to-Image Translation with Transformer (CVPR 2022)

This is the implementation of the paper Instance-Aware Image-to-Image Translation with Transformer by Kim et al.

You can check out project at [Project Page] and the paper on [arXiv].

Environment

• Python 3.8, PyTorch 1.11.0

Datasets

• INIT [dataset]

Training & Test Script

• train

train.py

• test

test.py

Config Path

config/base_train.yaml

config/base_test.yaml

BibTeX

If you find this research useful, please consider citing:

@inproceedings{kim2022instaformer,
  title={InstaFormer: Instance-Aware Image-to-Image Translation with Transformer},
  author={Kim, Soohyun and Baek, Jongbeom and Park, Jihye and Kim, Gyeongnyeon and Kim, Seungryong},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={18321--18331},
  year={2022}
}

instaformer's Issues

When will you update the code

I am very interested in this work. Hope you can release the training and testing code ASAP. Thanks in advance.

Missing data.py

I find that your forget to upload data.py. That's why we cannot get data.INIT_Dataset. Could you upload that ASAP?

training and test codes

When will the train and test codes be released. Thanks!

Test codes not released

When will you release the test codes? Thanks in advance!

用的是batch norm不是adain呀，作者请问可以解答下吗

miss html_lib

Hello excuse me, did you write this html_lib package, I can't find this package, trouble the author to help me answer thank you