Long Scale Error Control in Low Light Image and Video Enhancement Using Equivariance
This work addresses the challenge of enhancing dark images and videos for applications like photography or surveillance, representing an incremental advancement in restoration techniques.
The paper tackles the problem of low-light image and video enhancement by leveraging equivariance to improve color and light level restoration, showing improvements over state-of-the-art methods through quantitative and qualitative evaluations.
Image frames obtained in darkness are special. Just multiplying by a constant doesn't restore the image. Shot noise, quantization effects and camera non-linearities mean that colors and relative light levels are estimated poorly. Current methods learn a mapping using real dark-bright image pairs. These are very hard to capture. A recent paper has shown that simulated data pairs produce real improvements in restoration, likely because huge volumes of simulated data are easy to obtain. In this paper, we show that respecting equivariance -- the color of a restored pixel should be the same, however the image is cropped -- produces real improvements over the state of the art for restoration. We show that a scale selection mechanism can be used to improve reconstructions. Finally, we show that our approach produces improvements on video restoration as well. Our methods are evaluated both quantitatively and qualitatively.