返回
Toward Blind Flare Removal Using Knowledge-Driven Flare-Level Estimator
DOI:10.1109/TIP.2024.3480696.png)
摘要
En 中文
Lens flare is a common phenomenon when strong light rays arrive at the camera sensor and a clean scene is consequently mixed up with various opaque and semi-transparent artifacts. Existing deep learning methods are always constrained with limited real image pairs for training. Though recent synthesis-based approaches are found effective, synthesized pairs still deviate from the real ones as the mixing mechanism of flare artifacts and scenes in the wild always depends on a line of undetermined factors, such as lens structure, scratches, etc. In this paper, we present a new perspective from the blind nature of the flare removal task in a knowledge-driven manner. Specifically, we present a simple yet effective flare-level estimator to predict the corruption level of a flare-corrupted image. The estimated flare-level can be interpreted as additive information of the gap between corrupted images and their flare-free correspondences to facilitate a network at both training and testing stages adaptively. Besides, we utilize a flare-level modulator to better integrate the estimations into networks. We also devise a flare-aware block for more accurate flare recognition and reconstruction. Additionally, we collect a new real-world flare dataset for benchmarking, namely WiderFlare. Extensive experiments on three benchmark datasets demonstrate that our method outperforms state-of-the-art methods quantitatively and qualitatively.
Keyword:
Training
Scattering
Lenses
Image restoration
Cameras
Deep learning
Shape
Light sources
Image reconstruction
Feature extraction
Flare removal
flare-level estimation
image restoration
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
暂无机构信息
引用论文
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍?
A survey of human breast cancer sensitivity to growth inhibition by calmodulin antagonists in tissue culture人类乳腺癌对钙调蛋白拮抗剂在组织培养中对生长抑制的敏感性的调查

