Image Denoising
Image denoising aims to remove noise from images while preserving important details, improving image quality for various applications. Current research emphasizes developing robust and efficient denoising methods using deep learning architectures like convolutional neural networks (CNNs), transformers, and diffusion models, as well as refining traditional techniques like total variation (TV) minimization and non-local means (NLM). These advancements are crucial for enhancing the performance of computer vision systems across diverse fields, including medical imaging, remote sensing, and autonomous driving, where noisy data is prevalent. Furthermore, research explores unsupervised and self-supervised learning approaches to reduce reliance on large, labeled datasets.
Papers
Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches
Xin Lin, Chao Ren, Xiao Liu, Jie Huang, Yinjie Lei
Self-supervised Noise2noise Method Utilizing Corrupted Images with a Modular Network for LDCT Denoising
Yuting Zhu, Qiang He, Yudong Yao, Yueyang Teng