AI system CANVAS generates multi-sensory art descriptions

Researchers have developed CANVAS, an AI system designed to generate detailed, multi-sensory descriptions and synchronized audio narrations for visual artworks. This automated workflow aims to make art more accessible to blind and low-vision audiences by providing richer captions than traditional alt-text. Initial evaluations show that CANVAS produces descriptions with greater lexical diversity and narrative detail, and can process an artwork in under 20 seconds at a low cost. AI

影响 Enhances accessibility for visually impaired individuals in cultural institutions and digital collections.

排序理由 The cluster contains an academic paper detailing a new AI system and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• CANVAS
• Vignesh Nagarajan

• 论文
• 产品

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →