Variable-Rate Learned Image Compression with Multi-Objective Optimization and Quantization-Reconstruction Offsets

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kamisli, Fatih, Racape, Fabien, Choi, Hyomin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911786311090176
author Kamisli, Fatih
Racape, Fabien
Choi, Hyomin
author_facet Kamisli, Fatih
Racape, Fabien
Choi, Hyomin
contents Achieving successful variable bitrate compression with computationally simple algorithms from a single end-to-end learned image or video compression model remains a challenge. Many approaches have been proposed, including conditional auto-encoders, channel-adaptive gains for the latent tensor or uniformly quantizing all elements of the latent tensor. This paper follows the traditional approach to vary a single quantization step size to perform uniform quantization of all latent tensor elements. However, three modifications are proposed to improve the variable rate compression performance. First, multi objective optimization is used for (post) training. Second, a quantization-reconstruction offset is introduced into the quantization operation. Third, variable rate quantization is used also for the hyper latent. All these modifications can be made on a pre-trained single-rate compression model by performing post training. The algorithms are implemented into three well-known image compression models and the achieved variable rate compression results indicate negligible or minimal compression performance loss compared to training multiple models. (Codes will be shared at https://github.com/InterDigitalInc/CompressAI)
format Preprint
id arxiv_https___arxiv_org_abs_2402_18930
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Variable-Rate Learned Image Compression with Multi-Objective Optimization and Quantization-Reconstruction Offsets
Kamisli, Fatih
Racape, Fabien
Choi, Hyomin
Image and Video Processing
Computer Vision and Pattern Recognition
Achieving successful variable bitrate compression with computationally simple algorithms from a single end-to-end learned image or video compression model remains a challenge. Many approaches have been proposed, including conditional auto-encoders, channel-adaptive gains for the latent tensor or uniformly quantizing all elements of the latent tensor. This paper follows the traditional approach to vary a single quantization step size to perform uniform quantization of all latent tensor elements. However, three modifications are proposed to improve the variable rate compression performance. First, multi objective optimization is used for (post) training. Second, a quantization-reconstruction offset is introduced into the quantization operation. Third, variable rate quantization is used also for the hyper latent. All these modifications can be made on a pre-trained single-rate compression model by performing post training. The algorithms are implemented into three well-known image compression models and the achieved variable rate compression results indicate negligible or minimal compression performance loss compared to training multiple models. (Codes will be shared at https://github.com/InterDigitalInc/CompressAI)
title Variable-Rate Learned Image Compression with Multi-Objective Optimization and Quantization-Reconstruction Offsets
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.18930