arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.08641cs.CVcs.AIcs.HCcs.MM
收藏

关于生成艺术的象征性 grounded 解释性评估

On Semiotic-Grounded Interpretive Evaluation of Generative Art

The Hong Kong Polytechnic University(香港理工大学)

Ruixiang Jiang, Changwen Chen

AI总结:

本文提出SemJudge,通过层级象征图评估生成艺术的象征和指示意义,提升艺术解读深度,推动生成艺术向表达复杂人类经验发展。

摘要:

解释对于解读艺术语言至关重要:观众通过从视觉作品中恢复意义与艺术家沟通。然而,当前生成艺术(GenArt)评估者仍专注于表面图像质量或字面提示的遵守,未能评估创作者意图的深层象征或抽象意义。本文通过形式化一个皮尔士计算象征理论,将人类-生成艺术互动(HGI)建模为 cascaded semiosis。该框架揭示艺术意义通过三种模式——图标、象征和指示——传达,但现有评估者主要在图标模式中操作,对后两者结构上失明。为克服这种结构失明,我们提出SemJudge。该评估者通过层级象征图(HSG)显式评估HGI中的象征和指示意义,重建从提示到生成作品的意义生成过程。大量定量实验显示,SemJudge在解释密集的细艺术基准上比先前评估者更接近人类判断。用户研究进一步证明,SemJudge产生更深入、更有洞察力的艺术解读,从而为生成艺术从生成“漂亮”的图像向能够表达复杂人类经验的媒介发展铺平道路。项目页面:https://github.com/songrise/SemJudge。

英文摘要:

Interpretation is essential to deciphering the language of art: audiences communicate with artists by recovering meaning from visual artifacts. However, current Generative Art (GenArt) evaluators remain fixated on surface-level image quality or literal prompt adherence, failing to assess the deeper symbolic or abstract meaning intended by the creator. We address this gap by formalizing a Peircean computational semiotic theory that models Human-GenArt Interaction (HGI) as cascaded semiosis. This framework reveals that artistic meaning is conveyed through three modes - iconic, symbolic, and indexical - yet existing evaluators operate heavily within the iconic mode, remaining structurally blind to the latter two. To overcome this structural blindness, we propose SemJudge. This evaluator explicitly assesses symbolic and indexical meaning in HGI via a Hierarchical Semiosis Graph (HSG) that reconstructs the meaning-making process from prompt to generated artifact. Extensive quantitative experiments show that SemJudge aligns more closely with human judgments than prior evaluators on an interpretation-intensive fine-art benchmark. User studies further demonstrate that SemJudge produces deeper, more insightful artistic interpretations, thereby paving the way for GenArt to move beyond the generation of "pretty" images toward a medium capable of expressing complex human experience. Project page: https://github.com/songrise/SemJudge.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑