How to Train Neural Networks for Flare Removal
This work provides a method for training neural networks to remove lens flare, a common photographic artifact, which is a significant problem for photographers and image processing applications.
This paper addresses the challenge of lens flare removal in photographs by generating semi-synthetic datasets of flare-corrupted and clean images. This novel data synthesis approach enabled the first successful training of neural networks for lens flare removal, demonstrating good generalization to real-world flares.
When a camera is pointed at a strong light source, the resulting photograph may contain lens flare artifacts. Flares appear in a wide variety of patterns (halos, streaks, color bleeding, haze, etc.) and this diversity in appearance makes flare removal challenging. Existing analytical solutions make strong assumptions about the artifact's geometry or brightness, and therefore only work well on a small subset of flares. Machine learning techniques have shown success in removing other types of artifacts, like reflections, but have not been widely applied to flare removal due to the lack of training data. To solve this problem, we explicitly model the optical causes of flare either empirically or using wave optics, and generate semi-synthetic pairs of flare-corrupted and clean images. This enables us to train neural networks to remove lens flare for the first time. Experiments show our data synthesis approach is critical for accurate flare removal, and that models trained with our technique generalize well to real lens flares across different scenes, lighting conditions, and cameras.