Zxinze 89a638e345 | 1 year ago | |
---|---|---|
data | 1 year ago | |
models | 1 year ago | |
options | 1 year ago | |
util | 1 year ago | |
README.md | 1 year ago | |
run.txt | 1 year ago | |
test.py | 1 year ago | |
train.py | 1 year ago | |
umdsr_motivation.png | 1 year ago | |
umdsr_net.png | 1 year ago |
Dong Zhao 1; Jia Li 1,2,4; Hongyu Li 1; Long Xu 3,4
1 State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing 100191, China;
2 Key Laboratory of Solar Activity, National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100101, China;
3 National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China;
4 Peng Cheng Laboratory, Shenzhen 518000, China.
Mars exploration has become a hot spot in recent years and is still advancing rapidly. However, Mars has massive dust storms that may cover many areas of the planet and last for weeks or even months. The local/global dust storms are so influential that they can significantly reduce visibility, and thereby the images captured by the cameras on the Mars rover are degraded severely. This work presents an unsupervised Martian dust storm removal network via disentangled representation learning (DRL). The core idea of the DRL framework is to use the content encoder and dust storm encoder to disentangle the degraded images into content features (on domain-invariant space) and dust storm features (on domain-specific space). The dust storm features carry the full dust storm-relevant prior knowledge from the dust storm images. The `cleaned' content features can be effectively decoded to generate more natural, faithful, clear images. The primary advantages of this framework are twofold. First, it is among the first to perform unsupervised training in Martian dust storm removal with a single image, avoiding the synthetic data requirements. Second, the model can implicitly learn the dust storm-relevant prior knowledge from the real-world dust storm datasets, avoiding the design of the complicated handcrafted priors. Extensive experiments demonstrate the DRL framework's effectiveness and show the promising performance of our network for Martian dust storm removal.
python train.py --name /your-model-name/ --dataroot /your-data-path/ --which_model_netG dr_ca --dh_real --allmodel --batchSize 8 --ngf 32 --norm sswitch --gpu_ids 0,1
python test.py --name /your-model-name/ --dataroot /your-data-path/ --which_model_netG dr_ca --dh_real --allmodel --batchSize 1 --ngf 32 --norm sswitch --sb --how_many 1000
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》