Training-Free Continuous Bitrate Control for Scalable Image Coding for Humans and Machines

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tatsumi, Yui, Watanabe, Hiroshi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914619473264640
author Tatsumi, Yui
Watanabe, Hiroshi
author_facet Tatsumi, Yui
Watanabe, Hiroshi
contents Continuous variable-rate compression is highly demanded in real-world applications, but remains underexplored in scalable image coding for humans and machines. In this paper, we propose a training-free variable-rate scalable image coding framework. By adjusting quantization steps based on predicted scale values, the proposed method achieves continuous bitrate control while preserving high-scale information in the machine and enhancement layers. Experimental results demonstrate the effectiveness of the proposed method and highlight the importance of bitrate allocation between the two layers.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00158
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Training-Free Continuous Bitrate Control for Scalable Image Coding for Humans and Machines
Tatsumi, Yui
Watanabe, Hiroshi
Image and Video Processing
Computer Vision and Pattern Recognition
Continuous variable-rate compression is highly demanded in real-world applications, but remains underexplored in scalable image coding for humans and machines. In this paper, we propose a training-free variable-rate scalable image coding framework. By adjusting quantization steps based on predicted scale values, the proposed method achieves continuous bitrate control while preserving high-scale information in the machine and enhancement layers. Experimental results demonstrate the effectiveness of the proposed method and highlight the importance of bitrate allocation between the two layers.
title Training-Free Continuous Bitrate Control for Scalable Image Coding for Humans and Machines
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2606.00158