Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal
Yuwen He, Wei Wang, Wanyu Wang, Kui Jiang

TL;DR
This paper introduces a self-supervised neural network model that effectively disentangles and removes multiple co-occurring lens flares in nighttime images by modeling their physical relationships.
Contribution
It presents the first physical relationship model for co-occurring lens flares and a self-supervised network for joint flare removal without pre-training.
Findings
Effective removal of multiple flare types simultaneously
Outperforms existing specialized methods
Works without pre-training
Abstract
Lens flares arise from light reflection and refraction within sensor arrays, whose diverse types include glow, veiling glare, reflective flare and so on. Existing methods are specialized for one specific type only, and overlook the simultaneous occurrence of multiple typed lens flares, which is common in the real-world, e.g. coexistence of glow and displacement reflections from the same light source. These co-occurring lens flares cannot be effectively resolved by the simple combination of individual flare removal methods, since these coexisting flares originates from the same light source and are generated simultaneously within the same sensor array, exhibit a complex interdependence rather than simple additive relation. To model this interdependent flare relationship, our Nighttime Lens Flare Formation model is the first attempt to learn the intrinsic physical relationship between…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsOil, Gas, and Environmental Issues
MethodsActivation Normalization · Affine Coupling · Invertible 1x1 Convolution · Normalizing Flows · GLOW
