论文标题
Multiiearth 2022-通过一代模型的图像到图像翻译挑战的冠军解决方案
MultiEarth 2022 -- The Champion Solution for Image-to-Image Translation Challenge via Generation Models
论文作者
论文摘要
Multiiearth 2022图像到图像翻译挑战提供了一个受约束的测试床，用于使用给定的Sentinel-1 VV＆VH图像生成相应的RGB Sentinel-2图像。在这一挑战中，我们设计了各种一代模型，并发现Spade [1]和Pix2PixHD [2]模型可以执行我们的最佳结果。在我们的自我评估中，具有L1损失的Spade-2模型可以达到0.02194 MAE得分和31.092 PSNR DB。在我们的最后提交中，最佳模型可以在领导委员会中获得0.02795 MAE得分排名第一。
The MultiEarth 2022 Image-to-Image Translation challenge provides a well-constrained test bed for generating the corresponding RGB Sentinel-2 imagery with the given Sentinel-1 VV & VH imagery. In this challenge, we designed various generation models and found the SPADE [1] and pix2pixHD [2] models could perform our best results. In our self-evaluation, the SPADE-2 model with L1-loss can achieve 0.02194 MAE score and 31.092 PSNR dB. In our final submission, the best model can achieve 0.02795 MAE score ranked No.1 on the leader board.
