SUNLayer: Stable denoising with generative networks

2018/03/25 by Jin, Ruhui, Dustin G. Mixon, Mixon, Dustin G. +2
Computer Science · #Advanced Data Compression Techniques #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1803.09319

openalex publication_date 2018/03/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Deep neural networks are often used to implement powerful generative models for real-world data. Notable applications include image denoising, as well as other classical inverse problems like compressed sensing and super-resolution. To provide a rigorous but simplified analysis of generative models, in this work, we introduce an elegant theoretical framework based on spherical harmonics, namely SUNLayer. Our theoretical framework identifies explicit conditions on activation functions that guarantee denoising under local optimization. Numerical experiments examine the theoretical properties on commonly used activation functions and demonstrate their stable denoising performance.

Citations

• Ideal spatial adaptation by wavelet shrinkage
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Synthesizing the preferred inputs for neurons in neural networks via\n deep generator networks

Related

• Denoising: from classical methods to deep CNNs
• IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoising
• Universal Denoising Networks : A Novel CNN Architecture for Image\n Denoising
• Denoising: A Powerful Building-Block for Imaging, Inverse Problems, and Machine Learning
• Self-supervised denoising for massive noisy images