传统的神经网络非均匀性校正算法对噪声具有较好的自适应性，但当空间低频噪声较大时，校正效果明显下降。
The traditional neural network correction has a good adaptivity to the noise. But with a stronger low frequency space noise, the correction effect is very poor.
静校正量可以分解成低频和高频分量。
Static correction can be broken down into low-frequency and high-frequency components.
色彩校正帧图像使用所产生的亮度分量图像和低频亮度分量图像而被进行色彩校正。
The color correction frame image is color-corrected using the generated brightness component image and low-frequency brightness component image.
应用推荐