暗光增强背景：
Images captured by standard imaging devices often suffer from low visibility in non-uniform illuminated environments such as back lighting, nighttime and low-light indoor scene. Those images may lose information in under-exposed regions, making the image content invisible to human eyes. Since the camera dynamic range is limited, if we increase camera exposure to reveal the information of under-exposed regions, the well-exposed regions will be overexposed or even saturated
histogram-based:
Retinex-based:
1.Paper: “A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement”
提出假设：The current under-exposures image and the other different exposures image are highly correlated.
算法框架：Two stage
a.The first stage simulates the human eye to adjust the exposure, generating an multi-exposure image set.
b. The second stage simulates the human brain to fuse the generated images into the final enhanced result.
算法具体实现：Four Steps
a. we first employ the illumination estimation techniques to build the weight matrix for image fusion.
b. we derives our camera response model based on observation.
c. we find the optimal exposure for our camera response model to generate the synthetic image that is well-exposed in the regions where the original image is under-exposed.
d. we obtain the enhanced results by fusing the input image with the synthetic image using the weight matrix.
Logarithmic Image Processing methods:
filtering-based methods: