1.However, collecting high-quality reference maps in real-world scenarios is time-consuming and expensive.
出发点1:在低光照领域,从现实世界中获取高质量的参考照片进行监督学习,既费时又困难,成本昂贵。
因为获得低光环境的照片是容易的,而此低光照片对应的亮度较大的参考图片是难得的。
2.To tackle the issues of limited information in a single low-light image and the poor adaptability of handcrafted priors, we propose to leverage paired low-light instances to train the LIE network.
Additionally, twice-exposure images provide useful information for solving the LIE task. As a result, our solution can reduce the demand for handcrafted priors and improve the adaptability of the network.
The core insight of our approach is to sufficiently exploit priors from paired low-light images.
Those low-light image pairs share the same scene content but different illumination. Mathematically, Retinex decomposition with low-light image pairs can be expressed as:
创新点1:作者利用两张低光图片进行训练,以充分提取低光图片的信息。
instead of directly imposing the Retinex decomposition on original low-light images, we adopt a simple self-supervised mechanism to remove inappropriate features and implement the Retinex decomposition on the optimized image.
Note that, this paper does not focus on designing modernistic network structures. L-Net and R-Net are very similar and simple,
1.模型使用的L-Net与R-Net十分简单。整体架构只是单纯的卷积神经网络。
Apart from L-Net and R-Net, we introduce P-Net to remove inappropriate features from the original image. Specifically, the structure of the P-Net is identical to the R-Net.
2,P-Net被设计用于去除不合理特征。
Note that the projection loss needs to cooperate with the other constraints to avoid a trivial solution.i,e.,i1 = I1.
3.Projection Loss:最大程度限制去除不合理特征后的i1和原始低光图片I1的区别。
这个损失需要避免一个特例,即降噪后图片与原图相同,即未降噪。
Since sensor noise hidden in dark regions will be amplified when the contrast is improved.
In our method, the sensor noise can be implicitly removed by Eq. 1.