You've Seen Enough: Quality-Constrained Image Coding for Machines

2026-09-20

AI Summary

本文针对机器视觉系统的图像压缩问题，通过设定人类可接受的视觉质量上限并优化剩余编码容量以提升机器性能，提出了一种基于约束优化的方法。

Abstract

Visual data is increasingly consumed by machine-vision systems rather than by human observers. Image Coding for Machines (ICM) compresses images assuming the main observer is a computer vision application and that the human observer needs to inspect or validate the decisions. Inspired by just-noticeable distortion, which sets the quality to the just-acceptable level for human observers, we aim to cap the human-observed quality at a desired level, with the goal of using the remaining coding capacity to improve the machine performance. We recast joint compression-segmentation training as a constrained optimization problem in which the codec must meet a predefined acceptable target visual quality while a task term consumes the remaining coding capacity. We solve this by designing a penalty function to guide the quality to the desired target. We propose two penalty functions, an absolute function and a bilinear function, the latter applying a steeper slope once the target visual quality is exceeded. Experimental results show that, under the quality constraint, the proposed method achieves a BD-rate of $-22.82\%$ over an unconstrained joint rate--distortion--task optimization and $-29.81\%$ over a simple rate--distortion baseline, showcasing bitrate reduction with the same task performance. This is achieved while the codec also meets the target visual quality with a reasonable error and without adding any complexity overhead.

Problem

• Image Coding for Machines
• visual quality
• coding capacity
• machine performance

Innovation

• Quality-Constrained Image Coding
• Joint Compression-Segmentation Training
• Penalty Function
• Bilinear Function
• Bitrate Reduction