SINCO: A Novel structural regularizer for image compression using implicit neural representations

10/26/2022
by   Harry Gao, et al.
0

Implicit neural representations (INR) have been recently proposed as deep learning (DL) based solutions for image compression. An image can be compressed by training an INR model with fewer weights than the number of image pixels to map the coordinates of the image to corresponding pixel values. While traditional training approaches for INRs are based on enforcing pixel-wise image consistency, we propose to further improve image quality by using a new structural regularizer. We present structural regularization for INR compression (SINCO) as a novel INR method for image compression. SINCO imposes structural consistency of the compressed images to the groundtruth by using a segmentation network to penalize the discrepancy of segmentation masks predicted from compressed images. We validate SINCO on brain MRI images by showing that it can achieve better performance than some recent INR methods.

READ FULL TEXT

page 2

page 3

page 4

page 5

research
03/16/2018

Towards Image Understanding from Deep Compression without Decoding

Motivated by recent work on deep neural network (DNN)-based image compre...
research
02/06/2014

An Estimation Method of Measuring Image Quality for Compressed Images of Human Face

Nowadays digital image compression and decompression techniques are very...
research
02/17/2020

Discernible Compressed Images via Deep Perception Consistency

Image compression, as one of the fundamental low-level image processing ...
research
02/08/2023

Hyperspectral Image Compression Using Implicit Neural Representation

Hyperspectral images, which record the electromagnetic spectrum for a pi...
research
07/16/2023

Boundary-weighted logit consistency improves calibration of segmentation networks

Neural network prediction probabilities and accuracy are often only weak...
research
09/26/2020

Quantifying the effect of image compression on supervised learning applications in optical microscopy

The impressive growth of data throughput in optical microscopy has trigg...
research
08/07/2022

PS-NeRV: Patch-wise Stylized Neural Representations for Videos

We study how to represent a video with implicit neural representations (...

Please sign up or login with your details

Forgot password? Click here to reset