LIME: A Method for Low-light IMage Enhancement
About
When one captures images in low-light conditions, the images often suffer from low visibility. This poor quality may significantly degrade the performance of many computer vision and multimedia algorithms that are primarily designed for high-quality inputs. In this paper, we propose a very simple and effective method, named as LIME, to enhance low-light images. More concretely, the illumination of each pixel is first estimated individually by finding the maximum value in R, G and B channels. Further, we refine the initial illumination map by imposing a structure prior on it, as the final illumination map. Having the well-constructed illumination map, the enhancement can be achieved accordingly. Experiments on a number of challenging real-world low-light images are present to reveal the efficacy of our LIME and show its superiority over several state-of-the-arts.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Human Pose Estimation | ExLPose-OCN (test) | AP@0.5:0.95 (A7M3)33.2 | 23 | |
| Human Pose Estimation | ExLPose Low-light-normal (LL-N) | AP (IoU 0.5:0.95)31.9 | 22 | |
| Pose Estimation | ExLPose High low-light LL-H (test) | AP@0.5:0.9521.2 | 7 | |
| Pose Estimation | ExLPose LL-E Extreme low-light (test) | AP@0.5:0.957.6 | 7 | |
| Pose Estimation | ExLPose Average low-light LL-A (test) | AP (0.5:0.95)21.1 | 7 | |
| Pose Estimation | ExLPose Well-lit (test) | AP@0.5:0.9557.7 | 7 |