How to Train Neural Networks for Flare Removal
- URL: http://arxiv.org/abs/2011.12485v4
- Date: Fri, 8 Oct 2021 00:48:27 GMT
- Title: How to Train Neural Networks for Flare Removal
- Authors: Yicheng Wu, Qiurui He, Tianfan Xue, Rahul Garg, Jiawen Chen, Ashok
Veeraraghavan, Jonathan T. Barron
- Abstract summary: We train neural networks to remove lens flare for the first time.
Our data synthesis approach is critical for accurate flare removal.
Models trained with our technique generalize well to real lens flares across different scenes, lighting conditions, and cameras.
- Score: 45.51943926089249
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- Harmonizing Light and Darkness: A Symphony of Prior-guided Data Synthesis and Adaptive Focus for Nighttime Flare Removal [44.35766203309201]
Intense light sources often produce flares in captured images at night, which deteriorates the visual quality and negatively affects downstream applications.
In order to train an effective flare removal network, a reliable dataset is essential.
We synthesize a prior-guided dataset named Flare7K*, which contains multi-flare images where the brightness of flares adheres to the laws of illumination.
We propose a plug-and-play Adaptive Focus Module (AFM) that can adaptively mask the clean background areas and assist models in focusing on the regions severely affected by flares.
arXiv Detail & Related papers (2024-03-30T10:37:56Z) - Improving Lens Flare Removal with General Purpose Pipeline and Multiple
Light Sources Recovery [69.71080926778413]
flare artifacts can affect image visual quality and downstream computer vision tasks.
Current methods do not consider automatic exposure and tone mapping in image signal processing pipeline.
We propose a solution to improve the performance of lens flare removal by revisiting the ISP and design a more reliable light sources recovery strategy.
arXiv Detail & Related papers (2023-08-31T04:58:17Z) - Toward Real Flare Removal: A Comprehensive Pipeline and A New Benchmark [12.1632995709273]
We propose a well-developed methodology for generating data-pairs with flare deterioration.
The similarity of scattered flares and symmetric effect of reflected ghosts are realized.
We also construct a real-shot pipeline that respectively processes the effects of scattering and reflective flares.
arXiv Detail & Related papers (2023-06-28T02:57:25Z) - Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare
Removal and Beyond [77.72043833102191]
We introduce the first comprehensive nighttime flare removal dataset, consisting of 962 real-captured flare images (Flare-R) and 7,000 synthetic flares (Flare7K)
Compared to Flare7K, Flare7K++ is particularly effective in eliminating complicated degradation around the light source, which is intractable by using synthetic flares alone.
To address this issue, we additionally provide the annotations of light sources in Flare7K++ and propose a new end-to-end pipeline to preserve the light source while removing lens flares.
arXiv Detail & Related papers (2023-06-07T08:27:44Z) - Nighttime Smartphone Reflective Flare Removal Using Optical Center
Symmetry Prior [81.64647648269889]
Reflective flare is a phenomenon that occurs when light reflects inside lenses, causing bright spots or a "ghosting effect" in photos.
We propose an optical center symmetry prior, which suggests that the reflective flare and light source are always symmetrical around the lens's optical center.
We create the first reflective flare removal dataset called BracketFlare, which contains diverse and realistic reflective flare patterns.
arXiv Detail & Related papers (2023-03-27T09:44:40Z) - Flare7K: A Phenomenological Nighttime Flare Removal Dataset [83.38205781536578]
We introduce Flare7K, the first nighttime flare removal dataset.
It offers 5,000 scattering and 2,000 reflective flare images, consisting of 25 types of scattering flares and 10 types of reflective flares.
With the paired data, we can train deep models to restore flare-corrupted images taken in the real world effectively.
arXiv Detail & Related papers (2022-10-12T20:17:24Z) - Automatic Flare Spot Artifact Detection and Removal in Photographs [4.56877715768796]
Flare spot is one type of flare artifact caused by a number of conditions.
In this paper, we propose a robust computational method to automatically detect and remove flare spot artifacts.
arXiv Detail & Related papers (2021-03-07T15:51:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.