• Corpus ID: 238531781

How to Train Neural Networks for Flare Removal

  title={How to Train Neural Networks for Flare Removal},
  author={Yichen Wu and Qiurui He and Tianfan Xue and Rahul Garg and Jiawen Chen and Ashok Veeraraghavan and Jonathan T. Barron},
  • Yichen Wu, Qiurui He, +4 authors J. Barron
  • Published 25 November 2020
  • Engineering, Computer Science
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… 
1 Citations
Blind Image Decomposition
A novel task, which requires separating a superimposed image into constituent underlying images in a blind setting, that is, both the source components involved in mixing as well as the mixing mechanism are unknown, is presented and studied.


Automated Lens Flare Removal
1 Motivation Lens flare and ghosting can be prevalent artifacts when taking pictures of a scene with a direct bright light. Those artifacts are usually caused by internal reflections of the lens due
Automatic Flare Spot Artifact Detection and Removal in Photographs
This paper proposes a robust computational method to automatically detect and remove flare spot artifacts and defines a new confidence measure able to select flare spots among the candidates; and a method to accurately determine the flare region is given.
Unprocessing Images for Learned Raw Denoising
This work presents a technique to “unprocess” images by inverting each step of an image processing pipeline, thereby allowing us to synthesize realistic raw sensor measurements from commonly available Internet photos.
A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing
A deep neural network structure that exploits edge information in addressing representative low-level vision tasks such as layer separation and image filtering by estimating edges and reconstructing images using only cascaded convolutional layers arranged such that no handcrafted or application-specific image-processing components are required.
Veiling glare in high dynamic range imaging
This paper quantifies the presence of veiling glare and related optical artifacts for several types of digital cameras, and describes two methods for removing them: deconvolution by a measured glare spread function, and a novel direct-indirect separation of the lens transport using a structured occlusion mask.
Single Image Reflection Separation with Perceptual Losses
The approach uses a fully convolutional network trained end-to-end with losses that exploit low-level and high-level image information and proposes a novel exclusion loss that enforces pixel-level layer separation.
Single Image Haze Removal Using Dark Channel Prior
Haze brings troubles to many computer vision/graphics applications. It reduces the visibility of the scenes and lowers the reliability of outdoor surveillance systems; it reduces the clarity of the
Glare aware photography: 4D ray sampling for reducing glare effects of camera lenses
The approach handles photography looking into the sun and photos taken without a hood, removes the effect of lens smudges and reduces loss of contrast due to camera body reflections, and shows various applications in contrast enhancement and glare manipulation.
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer
This work proposes a robust training objective that is invariant to changes in depth range and scale, advocate the use of principled multi-objective learning to combine data from different sources, and highlights the importance of pretraining encoders on auxiliary tasks.
Auto Removal of Bright Spot from Images Captured Against Flashing Light Source
Experimental results reveal that the proposed method for determining the bright spot automatically and its removal by filling the gap is efficient and corrected images appear natural without any artifacts.