Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
yusi wang 4829ef572c | 2 years ago | |
---|---|---|
.. | ||
run_distribute_train.sh | 2 years ago | |
run_eval.sh | 2 years ago | |
run_standalone_train.sh | 2 years ago |
尽管使用更快更深的卷积神经网络在单图像超分辨率的准确性和速度方面取得了突破,但一个核心问题仍然很大程度上未解决:当我们在大的升级因子上超分辨时,我们如何恢复更精细的纹理细节?基于优化的超分辨率方法的行为主要由目标函数的选择驱动。近期工作主要集中在最小化均方重建误差。由此产生的估计具有高峰值信噪比,但它们通常缺乏高频细节,并且在感知上它们不能满足在较高分辨率下预期的保真度的感觉上不满意。在本文中,我们提出了SRGAN,一种用于图像超分辨率(SR)的生成对抗网络(GAN)。据我们所知,它是第一个能够推断4倍放大因子的照片般逼真的自然图像的框架。为实现这一目标,我们提出了一种感知损失函数,它包括对抗性损失和内容丢失。对抗性损失使用鉴别器网络将我们的解决方案推向自然图像流形,该网络经过训练以区分超分辨率图像和原始照片真实图像。另外,我们使用由感知相似性驱动的内容丢失而不是像素空间中的相似性。我们的深度残留网络能够在公共基准测试中从严重下采样的图像中恢复照片般逼真的纹理。广泛的平均意见得分(MOS)测试显示使用SRGAN在感知质量方面获得了巨大的显着提升。
Python Shell other
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》