论文概要
研究领域: CV 作者: Ziyu Zhai, Siyou Li, Juexi Shao, Juntao Yu 发布时间: 2026-05-07 arXiv: 2605.06641
中文摘要
开发陶瓷釉料是一个成本高昂、耗时的反复试错过程，复杂的化学特性给独立艺术家带来了沉重负担。虽然近期多模态AI的进步提供了现代化解决方案，但该领域缺乏训练这些模型所需的大规模数据集。我们提出了GlazyBench，这是首个用于AI辅助釉料设计的数据集。包含23,148个真实釉料配方，GlazyBench支持两个核心任务：从原材料预测烧制后的表面属性（如颜色、透明度），以及基于这些属性生成釉料的准确视觉表示。我们使用传统机器学习和大型语言模型建立了属性预测的综合基线，同时使用深度生成模型和大型多模态模型建立了图像生成基准。实验展示了有希望但具有挑战性的结果。GlazyBench开创了AI辅助材料设计的新研究方向，为系统评估提供了标准化基准。
原文摘要
Developing ceramic glazes is a costly, time-consuming process of trial and error due to complex chemistry, placing a significant burden on independent artists. While recent advances in multimodal AI offer a modern solution, the field lacks the large-scale datasets required to train these models. We propose GlazyBench, the first dataset for AI-assisted glaze design. Comprising 23,148 real glaze formulations, GlazyBench supports two primary tasks: predicting post-firing surface properties, such as color and transparency, from raw materials, and generating accurate visual representations of the glaze based on these properties. We establish comprehensive baselines for property prediction using traditional machine learning and large language models, alongside image generation benchmarks using d...
--- *自动采集于 2026-05-11*
#论文 #arXiv #CV #小凯