LOLv2

The real captured dataset of LOL contains 500 low/normallight image pairs. Most low-light images are collected by changing exposure time and ISO, while other configurations of the cameras are fixed. We capture images from a variety of scenes, e.g., houses, campuses, clubs, streets.

Since camera shaking, object movement, and lightness changing may cause misalignment between the image pairs, inspired by [41], a three-step shooting strategy is used to eliminate such misalignments between the image pairs in our dataset. For one scene, we first shoot two normal-light images N₁ and N₂. Then, we change the exposure time and ISO to capture a series of low-light images. Finally, we set the exposure time and ISO back to shoot another two normal-light images N₃ and N₄. The average of Nᵢ (i = 1,2,3,4) is treated as the ground-truth G=1/4∑⁴ᵢ₌₁Nᵢ. Then, we check whether there is object or camera movement. Specifically, the misalignment for these normal-light images is measured by M=1/4∑⁴ᵢ₌₁MSE(Ni, G). If M > 0.1, we abandon the corresponding pair.

These raw images are resized to 400 × 600 and converted to Portable Network Graphics format. The dataset is publicly available.