Perceptual impact of the loss function on deep-learning image coding performance

Nowadays, deep-learning image coding solutions have shown similar or better compression efficiency than conventional solutions based on hand-crafted transforms and spatial prediction techniques. These deep-learning codecs require a large training set of images and a training methodology to obtain a...

Full description

Saved in:
Bibliographic Details
Published in:Picture Coding Symposium pp. 37 - 41
Main Authors: Mohammadi, Shima, Ascenso, Joao
Format: Conference Proceeding
Language:English
Published: IEEE 07.12.2022
Subjects:
Codecs
Crowdsourcing
Image coding
Image quality
image quality metrics
Learning-based image compression
loss function
Measurement
percepual pptimization
Rate-distortion
Training
ISSN:2472-7822
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Nowadays, deep-learning image coding solutions have shown similar or better compression efficiency than conventional solutions based on hand-crafted transforms and spatial prediction techniques. These deep-learning codecs require a large training set of images and a training methodology to obtain a suitable model (set of parameters) for efficient compression. The training is performed with an optimization algorithm which provides a way to minimize the loss function. Therefore, the loss function plays a key role in the overall performance and includes a differentiable quality metric that attempts to mimic human perception. The main objective of this paper is to study the perceptual impact of several image quality metrics that can be used in the loss function of the training process, through a crowdsourcing subjective image quality assessment study. From this study, it is possible to conclude that the choice of the quality metric is critical for the perceptual performance of the deep-learning codec and that can vary depending on the image content.
ISSN:2472-7822
DOI:10.1109/PCS56426.2022.10018061