We study the problem of low lighting image en- hancement. Previous enhancement methods for images un- der low lighting conditions usually fail to consider the factor of image degradation during image formation. As a r...We study the problem of low lighting image en- hancement. Previous enhancement methods for images un- der low lighting conditions usually fail to consider the factor of image degradation during image formation. As a result, the lost contrast could not be recovered after enhancement. This paper will adaptively recover the contrast and adjust the exposure for low lighting images. Our first contribution is the modeling of image degradation in low lighting con- ditions. Then, the local maximum color value prior is pro- posed, i.e., in most regions of well exposed images, the lo- cal maximum color value of a pixel will be very high. By combining the image degradation model and local maximum color value prior, we propose to recover the un-degraded im- ages under low lighting conditions. Last, an adaptive expo- sure adjustment module is proposed to obtain the final result. We show that our approach enables better enhancement com- paring with popular image editing tools and academic algo- rithms.展开更多
文摘We study the problem of low lighting image en- hancement. Previous enhancement methods for images un- der low lighting conditions usually fail to consider the factor of image degradation during image formation. As a result, the lost contrast could not be recovered after enhancement. This paper will adaptively recover the contrast and adjust the exposure for low lighting images. Our first contribution is the modeling of image degradation in low lighting con- ditions. Then, the local maximum color value prior is pro- posed, i.e., in most regions of well exposed images, the lo- cal maximum color value of a pixel will be very high. By combining the image degradation model and local maximum color value prior, we propose to recover the un-degraded im- ages under low lighting conditions. Last, an adaptive expo- sure adjustment module is proposed to obtain the final result. We show that our approach enables better enhancement com- paring with popular image editing tools and academic algo- rithms.