Saliency Driven Perceptual Image Compression

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00350832" target="_blank" >RIV/68407700:21230/21:00350832 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/WACV48630.2021.00027" target="_blank" >https://doi.org/10.1109/WACV48630.2021.00027</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACV48630.2021.00027" target="_blank" >10.1109/WACV48630.2021.00027</a>

Result language

angličtina

Original language name

Saliency Driven Perceptual Image Compression

Original language description

This paper proposes a new end-to-end trainable model for lossy image compression, which includes several novel components. The method incorporates 1) an adequate perceptual similarity metric; 2) saliency in the images; 3) a hierarchical auto-regressive model. This paper demonstrates that the popularly used evaluations metrics such as MS-SSIM and PSNR are inadequate for judging the performance of image compression techniques as they do not align with the human perception of similarity. Alternatively, a new metric is proposed, which is learned on perceptual similarity data specific to image compression. The proposed compression model incorporates the salient regions and optimizes on the proposed perceptual similarity metric. The model not only generates images which are visually better but also gives superior performance for subsequent computer vision tasks such as object detection and segmentation when compared to existing engineered or learned compression techniques.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2021

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

ISBN

978-0-7381-4266-1

ISSN

2472-6737

e-ISSN

2642-9381

Number of pages

10

Pages from-to

227-236

Publisher name

Institute of Electrical and Electronics Engineers

Place of publication

New York

Event location

Waikoloa, HI

Event date

Jan 5, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000692171000023