- 2022.6.30 The draft is released now at http://arxiv.org/abs/2206.10910 SpA-Former:Transformer image shadow detection and removal via spatial attention
Modify the config.yml
to set your parameters and run:
python train.py
python predict.py --config <path_to_config.yml_in_the_out_dir> --test_dir <path_to_a_directory_stored_test_data> --out_dir <path_to_an_output_directory> --pretrained <path_to_a_pretrained_model> --cuda
There're my pre-trained models on ISTD(./pretrained_models/ISTD/gen_model_epoch_200.pth
)
Some results are shown as bellow and the images from left to right are: input, attention map, SpA-Former's output, ground truth.
Download the pretrained model shadow-removal Google-drive and Baidu Drive 提取码:rpis
Our test results: Google-drive and Baidu drive 提取码:18ut
To reproduce PSNR/SSIM/RMSE scores of the paper, run MATLAB script
evaluate.m
In this section, I compares SpA-Former with several methods using peak signal to noise ratio (PSNR) and structural similarity index (SSIM) and (RMSE) as metrics on datasets ISTD.
The code is updated on [https://github.com/Penn000/SpA-GAN_for_cloud_removal)]
Click official address Build the file structure as the folder data
shown. Here input
is the folder where the shadow image is stored and the folder target
stores the corresponding no shadow images.
./
+-- data
+-- ISTD_DATASET
+-- train
| +-- input
| | +-- 0.png
| | +-- ...
| +-- target
| +-- 0.png
| +-- ...
+-- test
+-- input
| +-- 0.png
| +-- ...
+-- target
+-- 0.png
+-- ...
Contact me if you have any questions about the code and its execution.
E-mail: SemiZxf@163.com
If you think this work is helpful for your research, give me a star :-D
@article{Xiao Feng Zhang,
title={SpA-Former: Transformer image shadow detection and removal via spatial attention},
author={Xiao Feng Zhang, Chao Chen Gu, Shan Ying Zhu},
journal={arXiv preprint arXiv:2206.10910},
year={2022}}