Towards Fast and Robust Real Image Denoising With Attentive Neural Network and PID Controller

• Published in: IEEE transactions on multimedia Vol. 24; pp. 2366 - 2377
• Main Authors: Ma, Ruijun, Li, Shuyi, Zhang, Bob, Li, Zhengming
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Algorithms; Controllers; Deep learning; Feature extraction; Feedback control; Image denoising; Image enhancement; Image quality; LSTM; Machine learning; Neural networks; Noise measurement; Noise reduction; PID Controller; Process control; Proportional integral derivative; Real-world Noisy Image; Robustness
• ISSN: 1520-9210; 1941-0077
• DOI: 10.1109/TMM.2021.3079697

With the development of deep learning technologies, recent research on real-world noisy image denoising has achieved a considerable improvement in performance. However, a common limitation for existing approaches is the imbalanced trade-off between denoising accuracy and efficiency. To address this problem, we propose a robust and efficient denoiser, called a hierarchical-based PID-attention denoising network (HPDNet), to flexibly deal with the sophisticated noise. The core of our algorithm is the PID-attentive recurrent network (PAR-Net) whose framework mainly consists of the LSTM network and PID controller. PAR-Net inherits the advantages of both the attentive recurrent network and control action, which can encourage more discriminatory feature representations. This learning procedure is implemented within a feedback control system, allowing a faster and more robust means to enhance feature discriminability. Furthermore, by decomposing the noisy image and stacking the PAR-Nets, our PAR-Net can work on a progressively hierarchical framework, and hence obtain multi-scale features and manageable successive refinements. On several widely used datasets, the proposed HPDNet demonstrates high efficiency, while delivering a better perceptually appealing image quality over state-of-the-art image denoising methods.