Department of Computer Engineering, Chosun University, Gwangju, South Korea.
PLoS One. 2023 Mar 9;18(3):e0282674. doi: 10.1371/journal.pone.0282674. eCollection 2023.
Ambient lighting conditions play a crucial role in determining the perceptual quality of images from photographic devices. In general, inadequate transmission light and undesired atmospheric conditions jointly degrade the image quality. If we know the desired ambient factors associated with the given low-light image, we can recover the enhanced image easily. Typical deep networks perform enhancement mappings without investigating the light distribution and color formulation properties. This leads to a lack of image instance-adaptive performance in practice. On the other hand, physical model-driven schemes suffer from the need for inherent decompositions and multiple objective minimizations. Moreover, the above approaches are rarely data efficient or free of postprediction tuning. Influenced by the above issues, this study presents a semisupervised training method using no-reference image quality metrics for low-light image restoration. We incorporate the classical haze distribution model to explore the physical properties of the given image to learn the effect of atmospheric components and minimize a single objective for restoration. We validate the performance of our network for six widely used low-light datasets. Experimental studies show that our proposed study achieves a competitive performance for no-reference metrics compared to current state-of-the-art methods. We also show the improved generalization performance of our proposed method which is efficient in preserving face identities in extreme low-light scenarios.
环境光照条件在确定摄影设备拍摄的图像的感知质量方面起着至关重要的作用。一般来说，不足的透射光和不理想的大气条件共同降低了图像质量。如果我们知道与给定低光图像相关的所需环境因素，我们可以轻松恢复增强后的图像。典型的深度网络在进行增强映射时，不会研究光分布和颜色构成特性。这导致在实际应用中缺乏图像实例自适应性能。另一方面，基于物理模型的方案受到固有分解和多个目标最小化的需求的影响。此外，上述方法很少具有数据效率或无需预测后调整。受上述问题的影响，本研究提出了一种使用无参考图像质量指标的半监督训练方法，用于低光图像恢复。我们结合经典的霾分布模型来探索给定图像的物理特性，以学习大气成分的影响并最小化恢复的单一目标。我们验证了我们的网络在六个广泛使用的低光数据集上的性能。实验研究表明，与当前最先进的方法相比，我们提出的研究在无参考指标方面具有竞争力的性能。我们还展示了我们提出的方法在极端低光情况下有效保留人脸身份的改进泛化性能。
