[论文] Can Vision Language Models Approximate Human Psychophysical Data on Pe...

论文概要

研究领域: CV 作者: Imad Ali Shah 发布时间: 2026-03-25 arXiv: 2603.24578

中文摘要

心理物理学实验仍然是感知图像质量评估（IQA）最可靠的方法，但其成本和有限的可扩展性鼓励采用自动化方法。我们调查视觉语言模型（VLMs）是否能够近似人类在三个图像质量尺度上的感知判断：对比度、色彩丰富度和整体偏好。

原文摘要

Psychophysical experiments remain the most reliable approach for perceptual image quality assessment (IQA), yet their cost and limited scalability encourage automated approaches. We investigate whether Vision Language Models (VLMs) can approximate human perceptual judgments across three image quality scales: contrast, colorfulness and overall preference.

--- *自动采集于 2026-03-27*

#论文 #arXiv #CV #小凯