Denoising Comparison Project

Filtering images such as color images, color videos, multispectral images and magnetic resonance images is challenging in terms of both effectiveness and efficiency. Leveraging the nonlocal self-similarity (NLSS) characteristic of images and sparse representation in the transform domain, the block-matching and 3D filtering (BM3D) based methods show powerful denoising performance. Recently, numerous new approaches with different regularization terms, transforms and advanced deep neural network (DNN) architectures are proposed to improve denoising quality. In this project, we extensively compare numerous on both synthetic and real-world datasets. We also work hard to collect new color image and video datasets for benchmarking, and our evaluations are performed from different perspectives. We will continuously update our datasets and denoising results of compared methods on this page.

• Denosing Results (Grayscale Images)
• Denosing Results (Color Images)
• Denosing Results (Color Videos)
• Denosing Results (MRI)
• Denosing Results (MSI)
• Denosing Results (HSI)