Flare7K++: mixing synthetic and real datasets for nighttime flare removal and beyond

• Main Authors: Dai, Yuekun, Li, Chongyi, Zhou, Shangchen, Feng, Ruicheng, Luo, Yihang, Loy, Chen Change
• Other Authors: College of Computing and Data Science
• Format: Article
• Language: English
• Published: 2025
• Subjects: Computer and Information Science; Low-level computer vision; Image restoration
• Online Access: https://hdl.handle.net/10356/183052

Artificial lights commonly leave strong lens flare artifacts on the images captured at night, degrading both the visual quality and performance of vision algorithms. Existing flare removal approaches mainly focus on removing daytime flares and fail in nighttime cases. Nighttime flare removal is chal...