Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Iwai, Shoma, Miyazaki, Tomo, Omachi, Shinichiro
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914813153640448
author Iwai, Shoma
Miyazaki, Tomo
Omachi, Shinichiro
author_facet Iwai, Shoma
Miyazaki, Tomo
Omachi, Shinichiro
contents In recent years, neural network-driven image compression (NIC) has gained significant attention. Some works adopt deep generative models such as GANs and diffusion models to enhance perceptual quality (realism). A critical obstacle of these generative NIC methods is that each model is optimized for a single bit rate. Consequently, multiple models are required to compress images to different bit rates, which is impractical for real-world applications. To tackle this issue, we propose a variable-rate generative NIC model. Specifically, we explore several discriminator designs tailored for the variable-rate approach and introduce a novel adversarial loss. Moreover, by incorporating the newly proposed multi-realism technique, our method allows the users to adjust the bit rate, distortion, and realism with a single model, achieving ultra-controllability. Unlike existing variable-rate generative NIC models, our method matches or surpasses the performance of state-of-the-art single-rate generative NIC models while covering a wide range of bit rates using just one model. Code will be available at https://github.com/iwa-shi/CRDR
format Preprint
id arxiv_https___arxiv_org_abs_2405_16817
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model
Iwai, Shoma
Miyazaki, Tomo
Omachi, Shinichiro
Computer Vision and Pattern Recognition
Image and Video Processing
In recent years, neural network-driven image compression (NIC) has gained significant attention. Some works adopt deep generative models such as GANs and diffusion models to enhance perceptual quality (realism). A critical obstacle of these generative NIC methods is that each model is optimized for a single bit rate. Consequently, multiple models are required to compress images to different bit rates, which is impractical for real-world applications. To tackle this issue, we propose a variable-rate generative NIC model. Specifically, we explore several discriminator designs tailored for the variable-rate approach and introduce a novel adversarial loss. Moreover, by incorporating the newly proposed multi-realism technique, our method allows the users to adjust the bit rate, distortion, and realism with a single model, achieving ultra-controllability. Unlike existing variable-rate generative NIC models, our method matches or surpasses the performance of state-of-the-art single-rate generative NIC models while covering a wide range of bit rates using just one model. Code will be available at https://github.com/iwa-shi/CRDR
title Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2405.16817