你已经看得够多了：面向机器的质量约束图像编码
You've Seen Enough: Quality-Constrained Image Coding for Machines
- Tampere University（坦佩雷大学）
- Nokia Technologies（诺基亚技术公司）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
本文提出一种面向机器图像编码的质量约束方法，通过惩罚函数将人类视觉质量限制在目标水平，利用剩余编码能力提升机器任务性能，在相同任务性能下显著降低比特率。
中文摘要 AI 辅助
视觉数据越来越多地被机器视觉系统而非人类观察者所消费。面向机器的图像编码（ICM）在假设主要观察者是计算机视觉应用且人类观察者需要检查或验证其决策的情况下压缩图像。受人类观察者恰可接受质量水平的恰可察觉失真启发，我们旨在将人类观察到的质量限制在期望水平，以利用剩余编码能力提升机器性能。我们将联合压缩-分割训练重新表述为一个约束优化问题，其中编解码器必须满足预定义的、可接受的视觉质量目标，而任务项消耗剩余的编码能力。我们通过设计一个惩罚函数来引导质量达到期望目标来解决这一问题。我们提出了两个惩罚函数：一个绝对值函数和一个双线性函数，后者在超过目标视觉质量后采用更陡的斜率。实验结果表明，在质量约束下，所提方法相对于无约束的联合率-失真-任务优化实现了$-22.82\%$的BD-rate，相对于简单的率-失真基线实现了$-29.81\%$的BD-rate，在相同任务性能下展示了比特率降低。同时，编解码器以合理的误差满足目标视觉质量，且不增加任何复杂度开销。
英文摘要
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, we cap human-observed quality at a desired level and devote the remaining bits to machine performance. Specifically, joint compression-segmentation training is recast 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. This paper proposes two variants of a penalty function that guides the quality toward the target: 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 BD-rates of $-22.82\%$ and $-29.81\%$ relative to an unconstrained joint rate--distortion--task optimization and a simple rate--distortion baseline, respectively, 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.
