Harmonizing Light and Darkness: A Symphony of Prior-guided Data Synthesis and Adaptive Focus for Nighttime Flare Removal
- URL: http://arxiv.org/abs/2404.00313v1
- Date: Sat, 30 Mar 2024 10:37:56 GMT
- Title: Harmonizing Light and Darkness: A Symphony of Prior-guided Data Synthesis and Adaptive Focus for Nighttime Flare Removal
- Authors: Lishen Qu, Shihao Zhou, Jinshan Pan, Jinglei Shi, Duosheng Chen, Jufeng Yang,
- Abstract summary: 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.
- Score: 44.35766203309201
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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. The mainstream flare removal datasets are semi-synthetic to reduce human labour, but these datasets do not cover typical scenarios involving multiple scattering flares. To tackle this issue, we synthesize a prior-guided dataset named Flare7K*, which contains multi-flare images where the brightness of flares adheres to the laws of illumination. Besides, flares tend to occupy localized regions of the image but existing networks perform flare removal on the entire image and sometimes modify clean areas incorrectly. Therefore, 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. Extensive experiments demonstrate that our data synthesis method can better simulate real-world scenes and several models equipped with AFM achieve state-of-the-art performance on the real-world test dataset.
Related papers
- MFDNet: Multi-Frequency Deflare Network for Efficient Nighttime Flare Removal [39.70102431268123]
We propose a lightweight Multi-Frequency Deflare Network (MFDNet) based on the Laplacian Pyramid.
Our network decomposes the flare-corrupted image into low and high-frequency bands, effectively separating the illumination and content information in the image.
Experimental results demonstrate that our approach outperforms state-of-the-art methods in removing nighttime flare on real-world and synthetic images.
arXiv Detail & Related papers (2024-06-26T05:31:36Z) - 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) - Enhancing Low-Light Images in Real World via Cross-Image Disentanglement [58.754943762945864]
We propose a new low-light image enhancement dataset consisting of misaligned training images with real-world corruptions.
Our model achieves state-of-the-art performances on both the newly proposed dataset and other popular low-light datasets.
arXiv Detail & Related papers (2022-01-10T03:12:52Z) - How to Train Neural Networks for Flare Removal [45.51943926089249]
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.
arXiv Detail & Related papers (2020-11-25T02:23:50Z) - Deep Lighting Environment Map Estimation from Spherical Panoramas [0.0]
We present a data-driven model that estimates an HDR lighting environment map from a single LDR monocular spherical panorama.
We exploit the availability of surface geometry to employ image-based relighting as a data generator and supervision mechanism.
arXiv Detail & Related papers (2020-05-16T14:23:05Z)
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.