Litcius/Paper detail

The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior

Yilin Liu, Jiang Li, Yunkui Pang, Dong Nie, Pew‐Thian Yap

202314 citationsDOIOpen Access PDF

Abstract

Deep Image Prior (DIP) shows that some network architectures inherently tend towards generating smooth images while resisting noise, a phenomenon known as spectral bias. Image denoising is a natural application of this property. Although denoising with DIP mitigates the need for large training sets, two often intertwined practical challenges need to be overcome: architectural design and noise fitting. Existing methods either handcraft or search for suitable architectures from a vast design space, due to the limited understanding of how architectural choices affect the denoising outcome. In this study, we demonstrate from a frequency perspective that unlearnt upsampling is the main driving force behind the denoising phenomenon with DIP. This finding leads to straightforward strategies for identifying a suitable architecture for every image without laborious search. Extensive experiments show that the estimated architectures achieve superior denoising results than existing methods with up to 95% fewer parameters. Thanks to this under-parameterization, the resulting architectures are less prone to noise-fitting.

Topics & Concepts

UpsamplingNoise reductionComputer scienceNoise (video)Artificial intelligenceImage (mathematics)ArchitectureImage denoisingNetwork architectureComputer visionVisual artsComputer securityArtImage and Signal Denoising MethodsAdvanced Image Fusion TechniquesAdvanced Image Processing Techniques