Flare Removal
13 papers with code • 1 benchmarks • 2 datasets
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.
Benchmarks
These leaderboards are used to track progress in Flare Removal
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Flare7K
Most implemented papers
How to Train Neural Networks for Flare Removal
google-research/google-research
•
•
ICCV 2021
When a camera is pointed at a strong light source, the resulting photograph may contain lens flare artifacts.
Light Source Guided Single-Image Flare Removal From Unpaired Data
tanmayj2020/LightSourceGuideSingleImageFlareRemoval-ICCV2021
•
•
ICCV 2021
In particular, we first detect the light source regions and the flare regions separately, and then remove the flare artifacts based on the light source aware guidance.
Automatic Flare Spot Artifact Detection and Removal in Photographs
Flare spot is one type of flare artifact caused by a number of conditions, frequently provoked by one or more high-luminance sources within or close to the camera field of view.
Flare7K: A Phenomenological Nighttime Flare Removal Dataset
ykdai/Flare7K
•
•
In this paper, we introduce, Flare7K, the first nighttime flare removal dataset, which is generated based on the observation and statistics of real-world nighttime lens flares.
Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light Sources Recovery
yuyanzhou1/improving-lens-flare-removal
•
•
ICCV 2023
In this paper, we propose a solution to improve the performance of lens flare removal by revisiting the ISP and remodeling the principle of automatic exposure in the synthesis pipeline and design a more reliable light sources recovery strategy.
Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior
ykdai/BracketFlare
•
•
CVPR 2023
With the dataset, neural networks can be trained to remove the reflective flares effectively.
Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond
ykdai/Flare7K
•
•
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.
Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recovery
yuyanzhou1/improving-lens-flare-removal
•
•
In this paper, we propose a solution to improve the performance of lens flare removal by revisiting the ISP and remodeling the principle of automatic exposure in the synthesis pipeline and design a more reliable light sources recovery strategy.
Toward Flare-Free Images: A Survey
yousefkotp/Flare-Free-Vision-Empowering-Uformer-with-Depth-Insights
•
•
Lens flare is a common image artifact that can significantly degrade image quality and affect the performance of computer vision systems due to a strong light source pointing at the camera.
Flare-Free Vision: Empowering Uformer with Depth Insights
yousefkotp/Flare-Free-Vision-Empowering-Uformer-with-Depth-Insights
•
•
ICASSP 2024
We propose a novel deep learning approach for flare removal that uses a combination of depth estimation and image restoration.
