视觉模型评估应以人为主，而非依赖单一指标。
Position: Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered
- 主张用人类感知替代单一客观指标评价视觉模型。
- 指出传统图像质量评估与真实用户偏好日益脱节。
- 适合关注用户体验和生成模型评估的研究者。
本文主张，现代视觉处理系统的评估不应再主要依赖单一图像质量评估指标，尤其在生成式与感知导向方法盛行的背景下。图像修复任务凸显了这一分歧：尽管客观指标能实现可复现、可扩展的评估，但其与人类感知和用户偏好之间的差距越来越大。这种不匹配可能限制创新，并误导视觉处理领域的研究方向。本文并非全盘否定指标，而是呼吁重新平衡评估范式，倡导更以人为中心、情境敏感且细粒度的视觉模型评估方式。
原文摘要 · Abstract (English)
This position paper argues that the evaluation of modern visual processing systems should no longer be driven primarily by single-metric image quality assessment benchmarks, particularly in the era of generative and perception-oriented methods. Image restoration exemplifies this divergence: while objective IQA metrics enable reproducible, scalable evaluation, they have increasingly drifted apart from human perception and user preferences. We contend that this mismatch risks constraining innovation and misguiding research progress across visual processing tasks. Rather than rejecting metrics altogether, this paper calls for a rebalancing of evaluation paradigms, advocating a more human-centered, context-aware, and fine-grained approach to assessing the visual models' outcomes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。