Flare7K: A Phenomenological Nighttime Flare Removal Dataset

12 Oct 2022  ·  Yuekun Dai, Chongyi Li, Shangchen Zhou, Ruicheng Feng, Chen Change Loy ·

Artificial lights commonly leave strong lens flare artifacts on images captured at night. Nighttime flare not only affects the visual quality but also degrades the performance of vision algorithms. Existing flare removal methods mainly focus on removing daytime flares and fail in nighttime. Nighttime flare removal is challenging because of the unique luminance and spectrum of artificial lights and the diverse patterns and image degradation of the flares captured at night. The scarcity of nighttime flare removal datasets limits the research on this crucial task. In this paper, we introduce, Flare7K, the first nighttime flare removal dataset, which is generated based on the observation and statistics of real-world nighttime lens flares. It offers 5,000 scattering and 2,000 reflective flare images, consisting of 25 types of scattering flares and 10 types of reflective flares. The 7,000 flare patterns can be randomly added to flare-free images, forming the flare-corrupted and flare-free image pairs. With the paired data, we can train deep models to restore flare-corrupted images taken in the real world effectively. Apart from abundant flare patterns, we also provide rich annotations, including the labeling of light source, glare with shimmer, reflective flare, and streak, which are commonly absent from existing datasets. Hence, our dataset can facilitate new work in nighttime flare removal and more fine-grained analysis of flare patterns. Extensive experiments show that our dataset adds diversity to existing flare datasets and pushes the frontier of nighttime flare removal.

PDF Abstract

Datasets


Introduced in the Paper:

Flare7K

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Flare Removal Flare7K Uformer PSNR 26.98 # 2
SSIM 0.890 # 2
LPIPS 0.047 # 2
Flare Removal Flare7K Wu PSNR 24.61 # 7
SSIM 0.871 # 7
LPIPS 0.060 # 7
Flare Removal Flare7K Sharma PSNR 20.49 # 9
SSIM 0.826 # 8
LPIPS 0.112 # 8
Flare Removal Flare7K Zhang PSNR 21.02 # 8
SSIM 0.784 # 9
LPIPS 0.174 # 9
Flare Removal Flare7K Restormer PSNR 26.28 # 4
SSIM 0.883 # 3
LPIPS 0.054 # 5
Flare Removal Flare7K MPRNet PSNR 26.14 # 5
SSIM 0.878 # 6
LPIPS 0.050 # 4
Flare Removal Flare7K HINet PSNR 26.74 # 3
SSIM 0.882 # 4
LPIPS 0.048 # 3
Flare Removal Flare7K U-Net PSNR 26.11 # 6
SSIM 0.879 # 5
LPIPS 0.055 # 6

Methods