LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal
This work addresses image quality degradation from lens flare for applications like autonomous driving, but it is incremental as it builds upon existing SIFR methods with a plug-and-play solution.
The paper tackles the problem of lens flare removal in images, particularly when off-frame light sources are incomplete, by proposing LightsOut, a diffusion-based outpainting framework that enhances existing methods, achieving consistent performance boosts across challenging scenarios without retraining.
Lens flare significantly degrades image quality, impacting critical computer vision tasks like object detection and autonomous driving. Recent Single Image Flare Removal (SIFR) methods perform poorly when off-frame light sources are incomplete or absent. We propose LightsOut, a diffusion-based outpainting framework tailored to enhance SIFR by reconstructing off-frame light sources. Our method leverages a multitask regression module and LoRA fine-tuned diffusion model to ensure realistic and physically consistent outpainting results. Comprehensive experiments demonstrate LightsOut consistently boosts the performance of existing SIFR methods across challenging scenarios without additional retraining, serving as a universally applicable plug-and-play preprocessing solution. Project page: https://ray-1026.github.io/lightsout/