Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images

Abstract

Modeling statistical regularity plays an essential role in ill-posed image processing problems. Recently, deep learning based methods have been presented to implicitly learn statistical representation of pixel distributions in natural images and leverage it as a constraint to facilitate subsequent tasks, such as color constancy and image dehazing. However, the existing CNN architecture is prone to variability and diversity of pixel intensity within and between local regions, which may result in inaccurate statistical representation. To address this problem, this paper presents a novel fully point-wise CNN architecture for modeling statistical regularities in natural images. Specifically, we propose to randomly shuffle the pixels in the origin images and leverage the shuffled image as input to make CNN more concerned with the statistical properties. Moreover, since the pixels in the shuffled image are independent identically distributed, we can replace all the large convolution kernels in CNN with point-wise ($1\ast 1$) convolution kernels while maintaining the representation ability. Experimental results on two applications: color constancy and image dehazing, demonstrate the superiority of our proposed network over the existing architectures, i.e., using 1/10$\sim$1/100 network parameters and computational cost while achieving comparable performance.

arXiv comment9 pages, 7 figures. To appear in ACM MM 2018

References in corpus (9)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Caffe: Convolutional Architecture for Fast Feature Embedding
• DehazeNet: An End-to-End System for Single Image Haze Removal
• Going Deeper with Convolutions
• An All-in-One Network for Dehazing and Beyond
• Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network
• Convolutional Color Constancy
• Color Constancy Using CNNs

Cited by in corpus (2)

• Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancement
• Semantic White Balance: Semantic Color Constancy Using Convolutional Neural Network