DeepAI
Log In Sign Up

NBNet: Noise Basis Learning for Image Denoising with Subspace Projection

12/30/2020
by   Shen Cheng, et al.
9

In this paper, we introduce NBNet, a novel framework for image denoising. Unlike previous works, we propose to tackle this challenging problem from a new perspective: noise reduction by image-adaptive projection. Specifically, we propose to train a network that can separate signal and noise by learning a set of reconstruction basis in the feature space. Subsequently, image denosing can be achieved by selecting corresponding basis of the signal subspace and projecting the input into such space. Our key insight is that projection can naturally maintain the local structure of input signal, especially for areas with low light or weak textures. Towards this end, we propose SSA, a non-local subspace attention module designed explicitly to learn the basis generation as well as the subspace projection. We further incorporate SSA with NBNet, a UNet structured network designed for end-to-end image denosing. We conduct evaluations on benchmarks, including SIDD and DND, and NBNet achieves state-of-the-art performance on PSNR and SSIM with significantly less computational cost.

READ FULL TEXT

page 3

page 4

page 7

page 8

page 12

page 13

08/25/2020

A Critical Analysis of Patch Similarity Based Image Denoising Algorithms

Image denoising is a classical signal processing problem that has receiv...
02/24/2017

Learning Non-local Image Diffusion for Image Denoising

Image diffusion plays a fundamental role for the task of image denoising...
05/24/2022

Thunder: Thumbnail based Fast Lightweight Image Denoising Network

To achieve promising results on removing noise from real-world images, m...
11/07/2012

James-Stein Type Center Pixel Weights for Non-Local Means Image Denoising

Non-Local Means (NLM) and variants have been proven to be effective and ...
03/16/2020

Gated Texture CNN for Efficient and Configurable Image Denoising

Convolutional neural network (CNN)-based image denoising methods typical...
06/09/2019

Fast Cadzow's Algorithm and a Gradient Variant

The Cadzow's algorithm is a signal denoising and recovery method which w...

Code Repositories

NBNet

NBNet: Noise Basis Learning for Image Denoising with Subspace Projection


view repo

NBNet_Pytorch

ReImplement of 'NBNet: Noise Basis Learning for Image Denoising with Subspace Projection' in Pytorch


view repo

NBNet

Pytorch implement "NBNet: Noise Basis Learning for Image Denoising with Subspace Projection"


view repo